
import numpy as np  # Library for numerical computations
import pandas as pd  # Library for data manipulation and analysis
import seaborn as sns  # Library for statistical data visualization
import matplotlib.pyplot as plt  # Library for creating plots and visualizations


# Import the necessary Plotly libraries
import plotly.graph_objects as go  # Low-level interface for creating Plotly plots
import plotly.express as px  # Higher-level interface for creating interactive plots


# Import the necessary ipywidgets libraries
import ipywidgets as widgets  # Library for creating interactive widgets
from ipywidgets import interact, interact_manual  # Functions for creating interactive controls


import warnings
warnings.filterwarnings('ignore')


import ipywidgets as widgets
from IPython.display import display, IFrame

# Dictionary of resource names and their corresponding URLs
resources = {
    "Coursera": "https://www.coursera.org/",
    "Kaggle": "https://www.kaggle.com",
    "Google Search": "https://www.google.com",
    "Statista": "https://www.statista.com",
    "World Bank": "https://www.data.worldbank.org",
    "Wikipedia": "https://www.wikipedia.org/"
}

# Dropdown widget to select the resource
resource_dropdown = widgets.Dropdown(
    options=list(resources.keys()),
    description='Select Resource:',
    layout=widgets.Layout(width='400px')
)

# Output widget to display the IFrame
output = widgets.Output()

# Function to update the IFrame based on the selected resource
def update_iframe(change):
    selected_resource = resource_dropdown.value
    with output:
        output.clear_output()
        display(IFrame(resources[selected_resource], width="100%", height="400px"))

# Attach the update function to the dropdown widget
resource_dropdown.observe(update_iframe, names='value')

# Display the dropdown widget and the output widget
display(resource_dropdown)
display(output)


import webbrowser

resources = {
    "Coursera": "https://www.coursera.org",
    "Kaggle": "https://www.kaggle.com",
    "Google Search": "https://www.google.com",
    "Statista": "https://www.statista.com",
    "World Bank": "https://data.worldbank.org"
}

# Function to open the web page in the default browser
def open_website(url):
    webbrowser.open_new_tab(url)

# Loop through the resources and open their websites
for resource, url in resources.items():
    print(f"Opening {resource} website: {url}")
    open_website(url)

Opening Coursera website: https://www.coursera.org
Opening Kaggle website: https://www.kaggle.com
Opening Google Search website: https://www.google.com
Opening Statista website: https://www.statista.com
Opening World Bank website: https://data.worldbank.org


# Reading the datasets into DataFrames

# Dataset 1: U.S. Presidents' Information
# Path: C:\Users\User\Desktop\GitHub-projects\projects\Data-Dives-Projects-Unleashed\dataSets\course 1\week 3\datasets\presidents\presidents.csv
pres_df_1 = pd.read_csv(r'C:\Users\User\Desktop\GitHub-projects\projects\Data-Dives-Projects-Unleashed\dataSets\course 1\week 3\datasets\presidents\presidents.csv')

# Dataset 2: First Ladies' Data
# Path: C:\Users\User\Desktop\GitHub-projects\projects\Data-Dives-Projects-Unleashed\dataSets\course 1\week 3\datasets\presidents\first_ladies.csv
pres_df_2 = pd.read_csv(r'C:\Users\User\Desktop\GitHub-projects\projects\Data-Dives-Projects-Unleashed\dataSets\course 1\week 3\datasets\presidents\first_ladies.csv')

# Dataset 3: Historical Presidents Physical Data (More)
# Path: C:\Users\User\Desktop\GitHub-projects\projects\Data-Dives-Projects-Unleashed\dataSets\course 1\week 3\datasets\presidents\Historical Presidents Physical Data (More).csv
pres_df_3 = pd.read_csv(r'C:\Users\User\Desktop\GitHub-projects\projects\Data-Dives-Projects-Unleashed\dataSets\course 1\week 3\datasets\presidents\Historical Presidents Physical Data (More).csv')

# Dataset 4: U.S. Presidents Dataset (1)
# Path: C:\Users\User\Desktop\GitHub-projects\projects\Data-Dives-Projects-Unleashed\dataSets\course 1\week 3\datasets\presidents\presidents(1).csv
pres_df_4 = pd.read_csv(r'C:\Users\User\Desktop\GitHub-projects\projects\Data-Dives-Projects-Unleashed\dataSets\course 1\week 3\datasets\presidents\presidents(1).csv')

# Dataset 5: U.S. Presidents Popular Vote Percentage Dataset (1)
# Path: C:\Users\User\Desktop\GitHub-projects\projects\Data-Dives-Projects-Unleashed\dataSets\course 1\week 3\datasets\presidents\pvp_dataset(1).csv
pres_df_5 = pd.read_csv(r'C:\Users\User\Desktop\GitHub-projects\projects\Data-Dives-Projects-Unleashed\dataSets\course 1\week 3\datasets\presidents\pvp_dataset(1).csv')

# Dataset 6: Most Common Names of U.S. Presidents (1789-2021) (1)
# Path: C:\Users\User\Desktop\GitHub-projects\projects\Data-Dives-Projects-Unleashed\dataSets\course 1\week 3\datasets\presidents\us_presidents.csv
pres_df_6 = pd.read_csv(r'C:\Users\User\Desktop\GitHub-projects\projects\Data-Dives-Projects-Unleashed\dataSets\course 1\week 3\datasets\presidents\us_presidents.csv')

# Dataset 7: USA Economy Growth Dataset
# Path: C:\Users\User\Desktop\GitHub-projects\projects\Data-Dives-Projects-Unleashed\dataSets\course 1\week 3\datasets\presidents\USA Economy Growth.csv
# Note: Using encoding='iso-8859-1' to handle non-utf-8 encoded characters
pres_df_7 = pd.read_csv(r'C:\Users\User\Desktop\GitHub-projects\projects\Data-Dives-Projects-Unleashed\dataSets\course 1\week 3\datasets\presidents\USA Economy Growth.csv', encoding='iso-8859-1')

# Dataset 8: U.S. GDP During Presidencies Dataset
# Path: C:\Users\User\Desktop\GitHub-projects\projects\Data-Dives-Projects-Unleashed\dataSets\course 1\week 3\datasets\presidents\USGDPpresidents.csv
pres_df_8 = pd.read_csv(r'C:\Users\User\Desktop\GitHub-projects\projects\Data-Dives-Projects-Unleashed\dataSets\course 1\week 3\datasets\presidents\USGDPpresidents.csv')


pres_df_1.head()


pres_df_1.head()


pres_df_2.head()


pres_df_3.head()


pres_df_4.head()


pres_df_5.head()


pres_df_6.head()


pres_df_7.head()


pres_df_8.head()


import pandas as pd
import matplotlib.pyplot as plt
import pandas_profiling
from ipywidgets import interact, widgets
from IPython.display import display, HTML


# Dictionary to store the dataset names and corresponding DataFrames
datasets = {
    "U.S. Presidents' Information": pres_df_1,
    "First Ladies' Data": pres_df_2,
    "Historical Presidents Physical Data (More)": pres_df_3,
    "U.S. Presidents Dataset (1)": pres_df_4,
    "U.S. Presidents Popular Vote Percentage Dataset (1)": pres_df_5,
    "Most Common Names of U.S. Presidents (1789-2021) (1)": pres_df_6,
    "USA Economy Growth Dataset": pres_df_7,
    "U.S. GDP During Presidencies Dataset": pres_df_8,
}

# Function to display dataset information, head, tail, and profiling report
@interact(dataset=datasets.keys(), show_head=True)
def display_dataset_info(dataset, show_head):
    df = datasets[dataset]

    # Display head or tail of the dataset based on user selection
    if show_head:
        display(df.head())
    else:
        display(df.tail())

# Plotting number of columns and rows (shape) with numbers on the bars
    rows, cols = df.shape
    shape_plot = pd.DataFrame({'Rows': [rows], 'Columns': [cols]})
    ax = shape_plot.plot(kind='bar', legend=True, title='Number of Rows and Columns', figsize=(8, 6))
    plt.xlabel('Dataset')
    plt.ylabel('Count')
    plt.xticks(rotation=0)

    # Adding numbers on top of the bars
    for index, value in enumerate(shape_plot['Rows']):
        ax.text(index, value, str(value), ha='center', va='bottom', fontsize=10)

    plt.show()
    
    # Displaying information about column types and missing values using pandas-profiling
    display(HTML(f"<h3>{dataset} Information:</h3>"))
    profile = pandas_profiling.ProfileReport(df, title=dataset)
    display(profile)


pres_df_1


pres_df_1.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 44 entries, 0 to 43
Data columns (total 8 columns):
 #   Column                     Non-Null Count  Dtype 
---  ------                     --------------  ----- 
 0   #                          44 non-null     int64 
 1   President                  44 non-null     object
 2   Born                       44 non-null     object
 3   Age atstart of presidency  44 non-null     object
 4   Age atend of presidency    44 non-null     object
 5   Post-presidencytimespan    36 non-null     object
 6   Died                       44 non-null     object
 7   Age                        44 non-null     object
dtypes: int64(1), object(7)
memory usage: 2.9+ KB


# Task 0: Rename the columns
# Rename the columns
pres_df_1 = pres_df_1.rename(columns={'Age atstart of presidency': 'Age at start of presidency', 
                                     'Age atend of presidency': 'Age at end of presidency', 'Post-presidencytimespan': 'Post-presidency timespan'})


# Task 1: Remove the redundant index
pres_df_1 = pres_df_1.drop(columns=['#'], axis=1)


# Task 3: Split the 'Age at start of presidency' column into separate columns for age and date

import re

# Function to split the 'Age at start of presidency' column into separate columns for age and date
def split_age_and_date(row):
    age_date = row['Age at start of presidency']
    age_match = re.search(r'\d+ years?, \d+ days?', age_date)
    date_match = re.search(r'[A-Za-z]{3} \d{1,2}, \d{4}', age_date)
    age = age_match.group() if age_match else ""
    date = date_match.group() if date_match else ""
    return pd.Series({'Age at Start of Presidency': age.strip(), 'Start Date': date.strip()})

pres_df_1[['Age at Start of Presidency', 'Start Date of presidency']] = pres_df_1.apply(split_age_and_date, axis=1)


pres_df_1['Start Age of presidency'] = (pres_df_1['Age at start of presidency'].str.split('days', expand=True))[0]

pres_df_1 = pres_df_1.drop(['Age at Start of Presidency','Age at start of presidency'], axis=1)

# Display the updated DataFrame after performing Task 5
pres_df_1.head()


# Task 4: Split the 'Age at end of presidency' column into separate columns for number with days and years, and the date
pres_df_1[['End of Presidency Age', 'End of Presidency Date']] = pres_df_1['Age at end of presidency'].str.split('days', expand=True)

# Remove leading and trailing whitespaces from 'End of Presidency Age' and 'End of Presidency Date' columns
pres_df_1['End of Presidency Age'] = pres_df_1['End of Presidency Age'].str.strip()
pres_df_1['End of Presidency Date'] = pres_df_1['End of Presidency Date'].str.strip()
pres_df_1 = pres_df_1.drop('Age at end of presidency',axis=1)
pres_df_1


# Task: Remove the [b] from the 'End of Presidency Date' column
pres_df_1['End of Presidency Date'] = pres_df_1['End of Presidency Date'].str.replace(r'\[b\]|\[e\]', '', regex=True)


# Task 5: Fill missing values in 'Post-presidency timespan' with 'Died in Office'
pres_df_1['Post-presidency timespan'].fillna('Died in Office', inplace=True)


# Task: Remove the [b], [c] and [d] from the 'Post-presidency timespan' column
pres_df_1['Post-presidency timespan'] = pres_df_1['Post-presidency timespan'].str.replace(r'\[b\]|\[c\]|\[d\]', '', regex=True)


# Task: Remove the [b] from the 'Born' column
pres_df_1['Born'] = pres_df_1['Born'].str.replace(r'\[b\]|\[a\]', '', regex=True)


# Task : Add the word "days" to 'Start Age of Presidency' and 'End of Presidency Age'
pres_df_1['Start Age of presidency'] = pres_df_1['Start Age of presidency'] + " days"
pres_df_1['End of Presidency Age'] = pres_df_1['End of Presidency Age'] + " days"


# Task 6: Add missing data for Presidents Trump and Biden
pres_df_1 = pres_df_1.append({'President': 'Donald J. Trump', 'Born': 'June 14, 1946', 'Start Age of presidency': '70 years, 220 days', 
                             'Post-presidency timespan': 'Living', 'Died': '(living)', 'Start Date of presidency': 'Jan 20 2017', 
                             'End of Presidency Age': '74 years, 222 days', 'End of Presidency Date': 'Jan 20, 2021','Age':'70 years, 220 days'}, 
                            ignore_index=True)

pres_df_1 = pres_df_1.append({'President': 'Joe Biden', 'Born': 'Nov 20 1942', 'Start Age of presidency': '77 years, 62 days',
                             'Post-presidency timespan': 'Living', 'Died': '(living)', 'Start Date of presidency': 'Jan 20, 2021', 
                             'End of Presidency Age': '81 years, 62 days', 'End of Presidency Date':'Nov 5, 2024','Age':'78 years, 61 days'}, 
                            ignore_index=True)


# Task 7:  Convert specified columns to datetime data
date_columns = ['Born', 'Died', 'Start Date of presidency', 'End of Presidency Date']
pres_df_1[date_columns] = pres_df_1[date_columns].apply(pd.to_datetime, errors='coerce')


# Task 7:  Convert specified columns to datetime data
# Function to convert 'number years, number days', 'Died in Office', 'Living', and 'number days' to timedelta
def convert_years_days_to_timedelta(row):
    if pd.notna(row):
        if 'Died' in row:
            return row  # Keep "Died in Office" intact
        elif 'Living' in row:
            return pd.NaT  # Handle "Living" case
        else:
            years_days = row.split(', ')
            years = int(years_days[0].split()[0]) if 'year' in years_days[0] else 0
            days = int(years_days[1].split()[0]) if len(years_days) > 1 and 'day' in years_days[1] else int(years_days[0].split()[0])
            return pd.Timedelta(days=years*365 + days)
    else:
        return pd.NaT

# Convert Age, Start Age of presidency, End of Presidency Age, and Post-presidency timespan to timedelta
timedelta_columns = ['Age', 'Start Age of presidency', 'End of Presidency Age', 'Post-presidency timespan']
pres_df_1[timedelta_columns] = pres_df_1[timedelta_columns].applymap(convert_years_days_to_timedelta)


pres_df_1


pres_df_1.dtypes

President                            object
Born                         datetime64[ns]
Post-presidency timespan             object
Died                         datetime64[ns]
Age                         timedelta64[ns]
Start Date of presidency     datetime64[ns]
Start Age of presidency     timedelta64[ns]
End of Presidency Age       timedelta64[ns]
End of Presidency Date       datetime64[ns]
dtype: object


pres_df_2


pres_df_2.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 53 entries, 0 to 52
Data columns (total 8 columns):
 #   Column         Non-Null Count  Dtype  
---  ------         --------------  -----  
 0   Unnamed: 0     53 non-null     int64  
 1   relation       53 non-null     object 
 2   name           53 non-null     object 
 3   president      53 non-null     object 
 4   born           53 non-null     object 
 5   death          48 non-null     object 
 6   age_of_death   48 non-null     float64
 7   marriage_date  42 non-null     object 
dtypes: float64(1), int64(1), object(6)
memory usage: 3.4+ KB


# Task 1: Drop the redundant index column
pres_df_2 = pres_df_2.drop(columns='Unnamed: 0', axis=1)


# Task 2: Rename the columns
pres_df_2.rename(columns={
    'relation': 'Relation to President',
    'name': 'First Lady Name',
    'president': 'President',
    'born': 'Date of Born, First Lady',
    'death': 'Date of Death, First Lady',
    'age_of_death': 'Age at Death, First Lady',
    'marriage_date': 'Date of Marriage'
}, inplace=True)


# Task 3: Convert the 'Date of Born, First Lady', 'Date of Death, First Lady', and 'Date of Marriage' columns to datetime
date_columns = ['Date of Born, First Lady', 'Date of Death, First Lady', 'Date of Marriage']
pres_df_2[date_columns] = pres_df_2[date_columns].apply(pd.to_datetime)


pres_df_2


# Set option to display all columns
pd.set_option('display.max_columns', None)
pres_df_3.head()


pres_df_3.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 45 entries, 0 to 44
Data columns (total 32 columns):
 #   Column                 Non-Null Count  Dtype  
---  ------                 --------------  -----  
 0   order                  45 non-null     object 
 1   name                   45 non-null     object 
 2   height_cm              45 non-null     int64  
 3   height_in              45 non-null     float64
 4   weight_kg              45 non-null     float64
 5   weight_lb              45 non-null     int64  
 6   body_mass_index        45 non-null     float64
 7   body_mass_index_range  45 non-null     object 
 8   birth_day              45 non-null     int64  
 9   birth_month            45 non-null     int64  
 10  birth_year             45 non-null     int64  
 11  birth_date             45 non-null     object 
 12  birthplace             45 non-null     object 
 13  birth_state            45 non-null     object 
 14  death_day              39 non-null     float64
 15  death_month            39 non-null     float64
 16  death_year             39 non-null     float64
 17  death_date             39 non-null     object 
 18  death_age              39 non-null     float64
 19  astrological_sign      45 non-null     object 
 20  term_begin_day         45 non-null     int64  
 21  term_begin_month       45 non-null     int64  
 22  term_begin_year        45 non-null     int64  
 23  term_begin_date        45 non-null     object 
 24  term_end_day           44 non-null     float64
 25  term_end_month         44 non-null     float64
 26  term_end_year          44 non-null     float64
 27  term_end_date          44 non-null     object 
 28  presidency_begin_age   45 non-null     int64  
 29  presidency_end_age     44 non-null     float64
 30  political_party        45 non-null     object 
 31  corrected_iq           42 non-null     float64
dtypes: float64(12), int64(9), object(11)
memory usage: 11.4+ KB


pres_df_1


# Task 1: Delete the redundant columns
columns_to_drop = ['birth_day', 'birth_month', 'birth_year', 'birth_date',
                   'death_day', 'death_month', 'death_year', 'death_date',
                   'term_begin_day', 'term_begin_month', 'term_begin_year', 'term_begin_date',
                   'term_end_day', 'term_end_month', 'term_end_year', 'term_end_date']

pres_df_3.drop(columns=columns_to_drop, inplace=True)


# Task 2: Rename the columns
column_mapping = {
    'name': 'President'
}
pres_df_3.rename(columns=column_mapping, inplace=True)


# Task 4: Convert data types to the correct types and handle missing data

# Convert 'order' column to integer
pres_df_3['order'] = pd.to_numeric(pres_df_3['order'], errors='coerce', downcast='integer')

# Convert 'death_age' column to float (if applicable)
pres_df_3['death_age'] = pres_df_3['death_age'].astype(float)

# Convert 'presidency_end_age' column to float
pres_df_3['presidency_end_age'] = pres_df_3['presidency_end_age'].astype(float)

# Convert 'corrected_iq' column to float (if applicable)
pres_df_3['corrected_iq'] = pres_df_3['corrected_iq'].astype(float)


pres_df_3.head()


pres_df_4


pres_df_4.dtypes

No.                    int64
Name                  object
Birthplace            object
Birthday              object
Life                  object
Height               float64
Children               int64
Religion              object
Higher Education      object
Occupation            object
Military Service      object
Term                  object
Party                 object
Vice President        object
Previous Office       object
Economy               object
Foreign Affairs       object
Military Activity     object
Other Events          object
Legacy                object
dtype: object


# understand Economy, Foreign Affairs, Military Activity, Other Events, Legacy
for i in range(0,46):
    print(pres_df_4['Legacy'].loc[i])
    print()

He is universally regarded as one of the greatest figures in U.S. history. “First in war, first in peace, and first in the hearts of his country”

One of the most experienced men ever to become President. Played a major role in the movement for independence. By the end of his term, he was unpopular, respected but not beloved.

Probably  the most intelligent man ever to occupy the White House. Of broad interests and activity, he exerted an immense influence on the future of the new nation.

His leadership in the War of 1812 was particularly inept. But  the young nation emerged united and strong, and Madison  enjoyed tremendous popularity and respect during his last years.

His presidency contributed to national defense and security. The Monroe Doctrine became a landmark in American foreign policy. His time in office was called the "Era of Good Feeling".

He had been an excellent Secretary of State, maybe the best in the history of the U.S. But as a President he was not allowed by a hostile Congress to be successful.

Historians see in him both the best and the worst of the new Republic. Associated with the movement toward increased popular participation in government, the "Jacksonian democracy".

An able man, but always regarded more as a shrewd politician and a manipulator. His Presidency was a failure. It was marked by the financial crisis, the Panic of 1837. He was called "Martin Van Ruin".

none

His presidency is held in low esteem but scored a victory, the Texas annexation.  Expelled from his party while in office and without followers was powerless and yet effective and rather underrated

Polk added more territory than had any other president except Thomas Jefferson and made U.S. a coast-to-coast nation.  He was one of the greatest presidents.

His blunt manner and unsophisticated style handicapped him as president. Because of his short tenure, Taylor is not considered to have strongly influenced the U.S.

Honest and hardworking but a pompous, colorless individual who rose far beyond his ability. The Compromise of 1850 preserved the Union for a while  but destroyed his career.

As president, he made many divisive decisions which were widely criticized and earned him a reputation as one of the worst presidents in U.S. history.

His administration was dominated by fighting between pro-and antislavery forces. Few presidents have entered office with more experience, and few have so decisively failed. Probably the worst president.

The greatest U.S. President. He won the Civil War and  preserved the Union. His twin policies, emancipation of slaves and reconciliation of North and South, were his greatest legacies.

His conflict with Congress and his impeachment weakened the Presidency for decades. He is  considered one the worst American presidents. But he got Alaska. And Reconstruction was a major policy…

An excellent general but a mediocre politician. He won the Civil War, but his Presidency was rather a failure with scandals and economic depression. History has been rather unfair to him.

An  effective president, ending military occupation of southern states; reforming the civil service, putting the country back on the gold standard, and starting the Gilded Age: enormous growth with serious social unrest.

In the 4 months before he was shot, he did not accomplish much. He served the second-shortest term of any President.
He endured Congress pressure on  executive appointments.

Despite his reputation as a leading spoilsmen in American politics, he proved to be a dignified and able administrator. A little-known presidency but no duty was neglected in his tenure and no problem alarmed the nation.

He won praise for his honesty, independence, integrity, and commitment to the principles of classical liberalism. He relentlessly fought political corruption, patronage, and bossism.

 He was an effective leader but the economy deteriorated. Inflation, joblessness  and labor unrest marked his presidency. His lackluster personality made his administration seem colorless.

His reforms made him an icon for conservatives but his efforts to stem economic depression were not successful, and the conservative means he used to settle internal industrial conflicts were unpopular.

His leadership and his actions affected profoundly the future of the USA. 
His victory on the Spanish-American war transformed the Presidency into an office of world leadership.

The first modern American president and one of the most dynamic and popular. He radically reformed the government and changed the political system. One of the top 5 presidents.

A good administrator but without exceptional political and leadership skills. He failed to rise adequately to the challenges of the times, despite his many strong qualities.

Effective leadership in instituting a progressive domestic program. His foreign policies were marked by victory in World War I and passionate promotion of the League of Nations.

Presided over one of the most corrupt administrations. Very popular as president, he was later regarded as one of the worst presidents. Hardworking though. He pushed a pro-business agenda.

A competent administrator and a shrewd politician.Very popular in a period of rapid growth and prosperity but perhaps too complacent and inactive despite signs of a Depression.

A qualified executive who failed to provide effective leadership in the most severe crisis. He could not halt and manage the Great Depression. His beliefs did not allow him to take drastic steps.

The longest and one of the most acclaimed presidencies in American history. He led the United States, with absolute success, out of the Great Depression and later in victory in the World War II.

Unexpectedly a very efficient replacement. Shaped the world after WW II, more than any other man.  He led  the successful transition from wartime to peacetime economy. Unpopular in the end, today he is ranked amongst the top presidents.

After a glorious military career, as president, he negotiated the end of the Korean War and pursued moderate policies. He presided over a period of growth and prosperity, at the peak of the Cold War.

His youth, vigor, and style brought a fresh air in the presidency. He revived the New Deal and Fair Deal programs  and continued containment to prevent  spread of communism (Vietnam, Cuba). His assassination shocked the world.

Passed his Great Society domestic programs and pushed "War on Poverty". He escalated U.S. involvement in Vietnam, sending more than 500,000 troops to fight. He left US deeply divided.

Although he ended U.S. involvement in the Vietnam War and won diplomatic agreements with the Soviet Union and China, he is remembered for Watergate and as the only president who resigned from office.

A congressional president whose historic role was to mop up -effectively- the dregs of the two most damaging episodes in the history of the modern White House: Watergate  and  Vietnam.

Intelligent and hardworking but a DC outsider.He pursued foreign policy with emphasis on  human rights and peace. He lost a 2nd term because of the Panama  Canal Treaty, the prolonged Iran hostage crisis and the stagnant economy.

While his aptitude for the job was often questioned, he was always very popular. Reaganomics stimulated growth but USA became the largest debtor. His confrontational policies  with the Soviets ended the Cold War shortly after he left office.

He took few domestic initiatives and the economy had problems, but was successful in foreign affairs, deposing Panama’s dictator Noriega and fighting the Gulf War in Iraq. The Cold War was ended in his watch.

The longest period of peacetime economic expansion in USA history. A not so distant period before the WTC fell, before U.S. troops bogged down in Iraq, before recession. And also before the scandals and the bitter partisan battles of the 1990s.

He left as one of the least popular and most divisive presidents in American history. The Iraq war, the bungled response to Hurricane Katrina, the 2008 economic crisis, has brought the worst collapse in America's reputation since WW II.

 Important changes on healthcare, education, climate. finance. Obamacare was a defining issue. Economy bounced back but growth was anemic. Foreign policy left the world more insecure.

Polarizing leadership style, controversial policies, and challenges to democratic institutions, resulting in a divided nation and impeachment.

none


# Task 1: Drop the existing index column
pres_df_4.drop(columns=['No.'], inplace=True)

# Task 2: Drop columns that we already have in other dataframes
pres_df_4.drop(columns=['Birthday', 'Life', 'Height'], inplace=True)


# Task 4: Rename the column "name" to "President"
pres_df_4.rename(columns={'Name': 'President'}, inplace=True)


pres_df_4.loc[pres_df_4['President'] == "George Washington", 'Party'] = "Unaffiliated"
pres_df_4.loc[pres_df_4['President'] == "John Tyler", 'Party'] = "Whig"


pres_df_5.head()


pres_df_5.dtypes

year               int64
name              object
party             object
term              object
salary             int64
position_title    object
dtype: object


# Function to modify the names
def modify_name(name):
    name_parts = name.split(',')
    first_name_parts = name_parts[1].split()
    
    # Get the first name
    first_name = first_name_parts[0]
    
    # Check if the first name is composed of two names
    if len(first_name_parts) > 1:
        second_name = first_name_parts[1][0]  # Take the first letter of the second name
    else:
        second_name = ""

    last_name = name_parts[0]

    try:
        # Check for suffix
        suffix = name_parts[2]
    except IndexError:
        suffix = ""
    if len(first_name_parts) > 1:
        new_name = f"{first_name} {second_name}. {last_name}"
    else:
        new_name = f"{first_name} {last_name}"
    # Create new name format
    #new_name = f"{first_name} {second_name} {last_name} {suffix}"
    return new_name.strip()

# Apply the modify_name function to the 'name' column
pres_df_5['President'] = pres_df_5['name'].apply(modify_name)

# Drop the original 'name' column
pres_df_5.drop(columns=['name'], inplace=True)


pres_df_5[pres_df_5['year']==2016]


pres_df_6


pres_df_6.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 45 entries, 0 to 44
Data columns (total 8 columns):
 #   Column      Non-Null Count  Dtype 
---  ------      --------------  ----- 
 0   Unnamed: 0  45 non-null     int64 
 1   S.No.       45 non-null     int64 
 2   start       45 non-null     object
 3   end         44 non-null     object
 4   president   45 non-null     object
 5   prior       45 non-null     object
 6   party       45 non-null     object
 7   vice        45 non-null     object
dtypes: int64(2), object(6)
memory usage: 2.9+ KB


pres_df_7.head()


pres_df_7['Presidents'].value_counts()

Ronald Reagan     8
Bill Clinton      8
George W. Bush    8
Barack Obama      8
George Bush       4
Donald Trump      4
Joe Biden         3
Name: Presidents, dtype: int64


# Set the option to display all columns
pd.set_option('display.max_columns', None)

pres_df_8.head()


pres_df_8.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 265 entries, 0 to 264
Data columns (total 21 columns):
 #   Column            Non-Null Count  Dtype  
---  ------            --------------  -----  
 0   Unnamed: 0        265 non-null    int64  
 1   Year              265 non-null    int64  
 2   CPI               248 non-null    float64
 3   GDPdeflator       231 non-null    float64
 4   population.K      249 non-null    float64
 5   realGDPperCapita  231 non-null    float64
 6   executive         265 non-null    object 
 7   war               56 non-null     object 
 8   battleDeaths      248 non-null    float64
 9   battleDeathsPMP   232 non-null    float64
 10  Keynes            265 non-null    int64  
 11  unemployment      222 non-null    float64
 12  unempSource       222 non-null    object 
 13  fedReceipts       231 non-null    float64
 14  fedOutlays        231 non-null    float64
 15  fedSurplus        231 non-null    float64
 16  fedDebt           232 non-null    float64
 17  fedReceipts_pGDP  230 non-null    float64
 18  fedOutlays_pGDP   230 non-null    float64
 19  fedSurplus_pGDP   230 non-null    float64
 20  fedDebt_pGDP      231 non-null    float64
dtypes: float64(15), int64(3), object(3)
memory usage: 43.6+ KB


# Task 2: We need to delete the column named "Unnamed: 0" as it seems to be an unnecessary index column.
pres_df_8.drop('Unnamed: 0', axis=1)


# Merge pres_df_1, pres_df_3, and pres_df_4 based on their indices
pres_merged_df = pres_df_1.merge(pres_df_3, left_index=True, right_index=True)
pres_merged_df = pres_merged_df.merge(pres_df_4, left_index=True, right_index=True)

# Check the result
pres_merged_df.head()


# Merge pres_df_1, pres_df_3, and pres_df_4 based on the column 'President'
pres_merged_df = pres_df_1.merge(pres_df_4, left_index=True, right_index=True)


pres_merged_df.head()


import plotly.graph_objects as go
import pandas as pd

# Define colors for each political_party with a dark theme
colors = {
    'Democratic': '#00BFFF',
    'Republican': '#FF6347',
    'Whig': '#00FF00',
    'Federalist': '#9932CC',
    'Democratic-Republican': '#FFD700',
    'National Union': '#00CED1',
    'Unaffiliated': '#A9A9A9'
}

# Create a scatter trace for each political_party
scatter_traces = []
for index, row in pres_merged_df.iterrows():
    party = row['Party']
    scatter_trace = go.Scatter(
        x=[row['Born']],
        y=[row['President_x']],
        mode='markers',
        marker=dict(color=colors[party], size=10, opacity=0.8),
        name=party,
        hovertext=f'President: {row["President_x"]}<br>Party: {party}<br>Born: {row["Born"]}'
    )
    scatter_traces.append(scatter_trace)

# Create the figure layout with a dark background
layout = go.Layout(
    title='Presidents and Their Birthplaces by Political Party',
    xaxis=dict(title='Date of Birth'),
    yaxis=dict(title='President'),
    hovermode='closest',
    showlegend=True,
    template='plotly_dark',  # Use the dark theme template
)

# Create the figure and add the traces and layout
fig = go.Figure(data=scatter_traces, layout=layout)

# Increase the plot size
fig.update_layout(width=1400, height=1400)

fig.update_traces(text=hover_text, hoverinfo='text')

# Show the plot
fig.show()


import plotly.graph_objects as go
import pandas as pd
from geopy.geocoders import Nominatim

# Geocode the birthplaces to get latitude and longitude
geolocator = Nominatim(user_agent='presidents_map')
pres_merged_df['location'] = pres_merged_df['Birthplace'].apply(geolocator.geocode)
pres_merged_df['latitude'] = pres_merged_df['location'].apply(lambda loc: loc.latitude if loc else None)
pres_merged_df['longitude'] = pres_merged_df['location'].apply(lambda loc: loc.longitude if loc else None)

# Define colors for each political_party
colors = {
    'Unaffiliated': '#A9A9A9',
    'Federalist': '#9932CC',
    'Democratic-Republican': '#FFD700',
    'Democratic': '#00BFFF',
    'Republican': '#FF6347',
}

# Create a scatter trace for each president
scatter_points = []
for _, row in pres_merged_df.iterrows():
    scatter_point = go.Scattergeo(
        locationmode='USA-states',
        lon=[row['longitude']],
        lat=[row['latitude']],
        text=f'President: {row["President_x"]}<br>Born: {row["Born"]}<br>Birthplace: {row["Birthplace"]}<br>Party: {row["Party"]}',
        marker=dict(
            size=10,
            color=colors.get(row['Party'], 'gray'),
            opacity=0.8,
            line=dict(width=1, color='white')
        ),
        name=row['Party'],
        hoverinfo='text'
    )
    scatter_points.append(scatter_point)

# Create the layout for the map with a larger size
layout = go.Layout(
    title='Birthplaces of U.S. Presidents by Political Party',
    geo=dict(
        scope='usa',
        projection=dict(type='albers usa'),
        showland=True,
        landcolor='rgb(250, 250, 250)',
        subunitcolor='rgb(217, 217, 217)',
        countrycolor='rgb(217, 217, 217)',
        showlakes=True,
        lakecolor='rgb(255, 255, 255)',
        showsubunits=True,
        showcountries=True,
        resolution=50,
        lonaxis=dict(range=[-130, -60]),
        lataxis=dict(range=[20, 50])
    ),
    width=1400,  # Set the width of the map to 1000 pixels
    height=800,  # Set the height of the map to 800 pixels
)

# Create the figure and add the scatter points and layout
fig = go.Figure(data=scatter_points, layout=layout)

# Show the interactive map
fig.show()


import plotly.graph_objects as go
import pandas as pd

# Function to convert a value to timedelta or None for special cases
def convert_to_timedelta(value):
    if pd.notna(value) and 'days' in str(value):
        return pd.to_timedelta(value)
    return None

# Convert the "Post-presidency timespan" column to timedeltas where possible
pres_merged_df['Post-presidency timespan'] = pres_merged_df['Post-presidency timespan'].apply(convert_to_timedelta)

# Calculate the number of days in the "Post-presidency timespan" column
pres_merged_df['Post-presidency days'] = pres_merged_df['Post-presidency timespan'].dt.days

# Convert the number of days to years
pres_merged_df['Post-presidency years'] = pres_merged_df['Post-presidency days'] / 365.25  # Account for leap years

# Sort the DataFrame by "Post-presidency days" in descending order
pres_merged_df.sort_values(by='Post-presidency days', ascending=False, inplace=True)

# Create a function to define the color of the bars based on the value
def get_bar_color(value):
    if pd.notna(value):
        if isinstance(value, pd.Timedelta):
            return 'lightcoral'  # Light red for numeric values
        else:
            return 'red'  # Red for "Died in Office"
    else:
        return 'lightgray'  # Gray for NaN (still living)

# Create the bar chart
fig = go.Figure()

fig.add_trace(go.Bar(
    x=pres_merged_df['President_x'],
    y=pres_merged_df['Post-presidency years'],
    marker=dict(color=[get_bar_color(value) for value in pres_merged_df['Post-presidency timespan']]),
))

# Customize the layout
fig.update_layout(
    title='Post-presidency Timespan of U.S. Presidents (in Years)',
    xaxis_title='President',
    yaxis_title='Years',
    hovermode='y',
    width=1200,  # Set the width of the chart to 1200 pixels
    height=600,  # Set the height of the chart to 600 pixels
)

# Hide the numbers on the bars
fig.update_traces(texttemplate=None, textposition='outside')

# Rotate the x-axis labels for better readability
fig.update_xaxes(tickangle=45)

# Show the interactive bar chart
fig.show()


import pandas as pd
import plotly.graph_objects as go
from ipywidgets import interact, widgets

# Assuming you have a DataFrame called 'pres_merged_df' containing the data
# with columns: 'President_x', 'Born', 'Died', and 'Party'

# Calculate the age of each president and create a new column 'Age'
pres_merged_df['Born'] = pd.to_datetime(pres_merged_df['Born'])
pres_merged_df['Died'] = pd.to_datetime(pres_merged_df['Died'])
pres_merged_df['Age'] = (pres_merged_df['Died'] - pres_merged_df['Born']).dt.days / 365

colors = {
    'Unaffiliated': '#A9A9A9',
    'Federalist': '#9932CC',
    'Democratic-Republican': '#FFD700',
    'Democratic': '#00BFFF',
    'Republican': '#FF6347',
}

# Function to plot the bar chart
def plot_age_by_party(selected_party):
    filtered_df = pres_merged_df[pres_merged_df['Party'] == selected_party]
    sorted_df = filtered_df.sort_values(by='Age', ascending=False)

    fig = go.Figure()
    fig.add_trace(go.Bar(
        x=sorted_df['President_x'],
        y=sorted_df['Age'],
        marker=dict(color=colors.get(selected_party, '#808080'))  # Use grey if color not found
    ))
    
    fig.update_layout(
        xaxis_tickangle=-45,
        title=f'Age of Presidents in {selected_party} Party (Sorted)',
        xaxis_title='President',
        yaxis_title='Age at Death',
        hovermode='x'
    )
    
    fig.show()

# Get unique political parties from the DataFrame
parties = pres_merged_df['Party'].unique()

# Create an interactive dropdown menu to select the party
interact(plot_age_by_party, selected_party=widgets.Dropdown(options=parties));


import pandas as pd
import plotly.express as px

# Assuming you have a DataFrame called 'pres_merged_df' containing the data
# with columns: 'President_x', 'Born', 'Start Date of presidency', and 'Party'

# Calculate the age of each president when they started their presidency
pres_merged_df['Age_at_Start'] = (pres_merged_df['Start Date of presidency'] - pres_merged_df['Born']).dt.days / 365

# Sort the DataFrame based on the age at the start of the presidency in ascending order
sorted_df = pres_merged_df.sort_values(by='Age_at_Start', ascending=False)

# Define colors for each political party
colors = {
    'Unaffiliated': '#A9A9A9',
    'Federalist': '#9932CC',
    'Democratic-Republican': '#FFD700',
    'Democratic': '#00BFFF',
    'Republican': '#FF6347',
}

# Create the horizontal bar chart using Plotly Express
fig = px.bar(
    sorted_df,
    x='Age_at_Start',
    y='President_x',
    color='Party',
    title='Age of U.S. Presidents at the Start of Presidency (Sorted)',
    labels={'Age_at_Start': 'Age at Start of Presidency', 'President_x': 'President'},
    color_discrete_map=colors,
)

# Customize the appearance of the chart
fig.update_layout(yaxis_title=None, xaxis_tickangle=-45, hovermode='y', plot_bgcolor='rgba(0, 0, 0, 0)',height = 1400)

# Show the chart
fig.show()


import pandas as pd
import plotly.graph_objects as go

# Assuming you have a DataFrame called 'pres_merged_df' containing the data
# with columns: 'President_x' and 'Children'

# Create the pie chart data
children_counts = pres_merged_df['Children'].value_counts()

# Function to generate custom text labels for the pie chart
def custom_label(val):
    if val == 1:
        return f'{val} child'
    else:
        return f'{val} children'

# Apply the custom text labels to the index of children_counts
labels_with_children = children_counts.index.map(custom_label)

# Create the pie chart trace
pie_chart_trace = go.Pie(
    labels=labels_with_children,
    values=children_counts.values,
    textinfo='percent+label',
    textfont=dict(size=12, color='white'),  # Set text color to white for better visibility
)

# Create the layout with a dark background using the plotly_dark template
layout = go.Layout(
    title='Number of Children of U.S. Presidents',
    template='plotly_dark',  # Set the plot template to a dark theme
)

# Create the figure and display the pie chart
fig = go.Figure(data=[pie_chart_trace], layout=layout)

# Customize the appearance of the chart
fig.update_layout(height = 800)

fig.show()


import pandas as pd
import plotly.graph_objects as go

# Assuming you have a DataFrame called 'pres_merged_df' containing the data
# with columns: 'President_x' and 'Children'

# Sort the DataFrame by the number of children in ascending order
sorted_df = pres_merged_df # .sort_values(by='Children', ascending=True)

# Create the bar chart trace
bar_chart_trace = go.Bar(
    x=sorted_df['President_x'],
    y=sorted_df['Children'],
    text=sorted_df['Children'],
    textposition='outside',  # Display the number of children above the bars
    textfont=dict(size=12, color='white'),  # Set text color to white for better visibility
    marker=dict(color='dodgerblue'),  # Set the color of the bars
)

# Create the layout with a dark background using the plotly_dark template
layout = go.Layout(
    title='Number of Children of U.S. Presidents',
    xaxis=dict(title='President', tickangle=-45),  # Rotate tick labels by -45 degrees
    yaxis=dict(title='Number of Children'),
    template='plotly_dark',  # Set the plot template to a dark theme
)

# Create the figure and display the bar chart
fig = go.Figure(data=[bar_chart_trace], layout=layout)

# Customize the appearance of the chart
fig.update_layout(height = 600)

fig.show()


import pandas as pd
import plotly.graph_objects as go

# Assuming you have a DataFrame called 'pres_merged_df' containing the data
# with columns: 'President_x' and 'Children'

# Sort the DataFrame by the number of children in ascending order
sorted_df = pres_merged_df.sort_values(by='Children', ascending=True)

# Create the bar chart trace
bar_chart_trace = go.Bar(
    x=sorted_df['President_x'],
    y=sorted_df['Children'],
    text=sorted_df['Children'],
    textposition='outside',  # Display the number of children above the bars
    textfont=dict(size=12, color='white'),  # Set text color to white for better visibility
    marker=dict(color='dodgerblue'),  # Set the color of the bars
)

# Create the layout with a dark background using the plotly_dark template
layout = go.Layout(
    title='Number of Children of U.S. Presidents',
    xaxis=dict(title='President', tickangle=-45),  # Rotate tick labels by -45 degrees
    yaxis=dict(title='Number of Children'),
    template='plotly_dark',  # Set the plot template to a dark theme
)

# Create the figure and display the bar chart
fig = go.Figure(data=[bar_chart_trace], layout=layout)

# Customize the appearance of the chart
fig.update_layout(height = 600)

fig.show()


import pandas as pd
from ipywidgets import interact, widgets

# Assuming you have a DataFrame called 'pres_merged_df' containing the data
# with columns: 'President_x' and 'Religion'

# Function to display the list of presidents following a specific religion
def presidents_by_religion(selected_religion):
    presidents_list = pres_merged_df[pres_merged_df['Religion'] == selected_religion]['President_x'].tolist()
    if len(presidents_list) > 0:
        presidents = ', '.join(presidents_list)
        print(f"The U.S. Presidents following {selected_religion} are: {presidents}.")
    else:
        print(f"No U.S. Presidents were found following {selected_religion}.")

# Get unique religions from the DataFrame
religions = pres_merged_df['Religion'].unique()

# Create an interactive dropdown menu to select the religion
interact(presidents_by_religion, selected_religion=widgets.Dropdown(options=religions));


import pandas as pd
import plotly.express as px
from ipywidgets import interact, widgets

# Assuming you have a DataFrame called 'pres_merged_df' containing the data
# with columns: 'President_x', 'Religion', and 'Party'

# Function to plot the bar chart
def plot_presidents_by_religion(selected_religion):
    filtered_df = pres_merged_df[pres_merged_df['Religion'] == selected_religion]
    fig = px.bar(
        filtered_df,
        x='President_x',
        y='Party',
        title=f'U.S. Presidents Following {selected_religion}',
        labels={'President_x': 'President', 'Party': 'Political Party'},
        orientation='h',  # Horizontal bar chart
        template='plotly_dark',  # Set the plot template to a dark theme
        color='Party',  # Color based on the party
        color_discrete_map={
            'Unaffiliated': '#A9A9A9',
            'Federalist': '#9932CC',
            'Democratic-Republican': '#FFD700',
            'Democratic': '#00BFFF',
            'Republican': '#FF6347',
            'National Union': 'gray',
            'Whig':'orange'
            
        }  # Custom colors for each party
    )
    fig.update_layout(xaxis_tickangle=-45, hovermode='x')
    fig.show()

# Get unique religions from the DataFrame
religions = pres_merged_df['Religion'].unique()

# Create an interactive dropdown menu to select the religion
interact(plot_presidents_by_religion, selected_religion=widgets.Dropdown(options=religions));


import pandas as pd
import plotly.express as px
from ipywidgets import interact, widgets

# Assuming you have a DataFrame called 'pres_merged_df' containing the data
# with columns: 'President_x', 'Religion', and 'Party'

# Function to plot the bar chart
def plot_presidents_by_religion(selected_religion):
    filtered_df = pres_merged_df[pres_merged_df['Religion'] == selected_religion]
    fig = px.bar(
        filtered_df,
        x='Party',
        y='President_x',
        title=f'U.S. Presidents Following {selected_religion}',
        labels={'Party': 'Political Party', 'President_x': 'President'},
        orientation='h',  # Horizontal bar chart
        template='plotly_dark',  # Set the plot template to a dark theme
        color='Party',  # Color based on the party
        color_discrete_map={
            'Unaffiliated': '#A9A9A9',
            'Federalist': '#9932CC',
            'Democratic-Republican': '#FFD700',
            'Democratic': '#00BFFF',
            'Republican': '#FF6347',
            'National Union': 'gray',
            'Whig':'orange'
        }  # Custom colors for each party
    )
    fig.update_layout(xaxis_tickangle=-45, hovermode='x')
    fig.show()

# Get unique religions from the DataFrame
religions = pres_merged_df['Religion'].unique()

# Create an interactive dropdown menu to select the religion
interact(plot_presidents_by_religion, selected_religion=widgets.Dropdown(options=religions));


import pandas as pd
import plotly.graph_objects as go

# Assuming you have a DataFrame called 'pres_merged_df' containing the data
# with columns: 'President_x' and 'Religion'

# Create the pie chart data
religion_counts = pres_merged_df['Religion'].value_counts()

# Function to generate custom text labels for the pie chart
def custom_label(val):
    if val == 1:
        return f'{val} religion'
    else:
        return f'{val} religions'

# Apply the custom text labels to the index of religion_counts
labels_with_religions = religion_counts.index.map(custom_label)

# Create the pie chart trace
pie_chart_trace = go.Pie(
    labels=labels_with_religions,
    values=religion_counts.values,
    textinfo='percent+label',
    textfont=dict(size=12, color='white'),  # Set text color to white for better visibility
)

# Create the layout with a dark background using the plotly_dark template
layout = go.Layout(
    title='Religions of U.S. Presidents',
    template='plotly_dark',  # Set the plot template to a dark theme
)

# Create the figure and display the pie chart
fig = go.Figure(data=[pie_chart_trace], layout=layout)

# Customize the appearance of the chart
fig.update_layout(height=800)

fig.show()


import pandas as pd
from wordcloud import WordCloud
import matplotlib.pyplot as plt

# Assuming you have a DataFrame called 'pres_merged_df' containing the data
# with columns: 'President_x' and 'Higher Education'

# Concatenate all the 'Higher Education' values into a single string
education_text = ' '.join(pres_merged_df['Higher Education'].dropna())

# Create the Word Cloud with custom settings
wordcloud = WordCloud(
    width=1200,
    height=600,
    background_color='black',
    colormap='viridis',  # Choose a color map for the Word Cloud
    contour_color='steelblue',  # Set contour color for better visibility
    contour_width=2,  # Set contour width
    max_words=150,  # Set the maximum number of words in the Word Cloud
    prefer_horizontal=0.8,  # Set the ratio of horizontal to vertical words
).generate(education_text)

# Display the Word Cloud using matplotlib
plt.figure(figsize=(24, 12))
plt.imshow(wordcloud, interpolation='bilinear')
plt.axis('off')
plt.title("Higher Education of U.S. Presidents - Word Cloud", fontsize=20, color='white')
plt.show()


import pandas as pd
from matplotlib import pyplot as plt
from matplotlib_venn import venn2

# Assuming you have a DataFrame called 'pres_merged_df' containing the data
# with columns: 'President_x' and 'Higher Education'

# Filter out missing data
pres_merged_df = pres_merged_df.dropna(subset=['Higher Education'])

# Separate the educational institutions into two groups: Ivy League and Non-Ivy League
ivy_league = ['Harvard', 'Yale', 'Princeton', 'Columbia', 'Brown', 'Dartmouth', 'Cornell', 'University of Pennsylvania']
non_ivy_league = [edu for edu in pres_merged_df['Higher Education'].values if edu not in ivy_league]

# Create the Venn Diagram
plt.figure(figsize=(10, 8))  # Set the figure size to make the Venn Diagram bigger
venn2(subsets=(set(ivy_league), set(non_ivy_league)), set_labels=('Ivy League', 'Non-Ivy League'))

# Add title and legend
plt.title('Educational Background of U.S. Presidents - Ivy League vs. Non-Ivy League', fontsize=16)
plt.legend(['Ivy League', 'Non-Ivy League'], fontsize=14)

# Display the Venn Diagram
plt.show()


import pandas as pd
import plotly.graph_objects as go
from ipywidgets import interact, widgets

# Assuming you have a DataFrame called 'pres_merged_df' containing the data
# with columns: 'President_x' and 'Higher Education'

# Filter out missing data
pres_merged_df = pres_merged_df.dropna(subset=['Higher Education'])

# Create a dictionary to map presidents to their higher education values
president_higher_edu_dict = dict(zip(pres_merged_df['President_x'], pres_merged_df['Higher Education']))

# Function to plot the higher education value for a specific president
def plot_higher_education(president_name):
    higher_education = president_higher_edu_dict.get(president_name, 'Higher education data not available')

    # Create the plot
    fig = go.Figure()

    # Add a text annotation to display the higher education value
    fig.add_annotation(
        text=f"Higher Education: <span style='color: #2b9434;'>{higher_education}</span>",
        xref="paper",
        yref="paper",
        x=0.5,
        y=0.5,
        showarrow=False,
        font=dict(size=16),
        align='center',
    )

    # Update layout for better appearance
    fig.update_layout(
        title=f"Higher Education of U.S. President - {president_name}",
        xaxis=dict(visible=False),
        yaxis=dict(visible=False),
        width=1400,
        height=400,
        template='plotly_dark',  # Use dark theme
        margin=dict(t=100),
    )

    # Show the plot
    fig.show()

# Get unique president names from the DataFrame
president_names = pres_merged_df['President_x'].unique()

# Create an interactive dropdown menu to select the president
interact(plot_higher_education, president_name=widgets.Dropdown(options=president_names));


import pandas as pd
from wordcloud import WordCloud
import matplotlib.pyplot as plt

# Assuming you have a DataFrame called 'pres_merged_df' containing the data
# with column 'Occupation' and other relevant columns

# Split the values in the 'Occupation' column and create a new DataFrame with all the occupations
occupations_df = pres_merged_df['Occupation'].str.split(', ', expand=True)

# Flatten the DataFrame into a single Series and get the value counts
occupation_counts = occupations_df.melt(value_name='Occupation').groupby('Occupation').size()

# Sort the occupations by frequency in descending order
top_occupations = occupation_counts.sort_values(ascending=False).head(4)

# Create the Word Cloud with custom settings
wordcloud = WordCloud(
    width=1200,
    height=600,
    background_color='black',
    colormap='viridis',  # Choose a color map for the Word Cloud
    contour_color='steelblue',  # Set contour color for better visibility
    contour_width=2,  # Set contour width
    max_words=150,  # Set the maximum number of words in the Word Cloud
    prefer_horizontal=0.8,  # Set the ratio of horizontal to vertical words
).generate_from_frequencies(top_occupations)

# Display the Word Cloud using matplotlib
plt.figure(figsize=(24, 12))
plt.imshow(wordcloud, interpolation='bilinear')
plt.axis('off')
plt.title("Top 4 Occupations of U.S. Presidents - Word Cloud", fontsize=20, color='white')
plt.show()


import pandas as pd
import plotly.express as px

# Assuming you have a DataFrame called 'pres_merged_df' containing the data
# with the column 'Occupation' and other relevant columns

# Split the values in the 'Occupation' column and create a new DataFrame with all the occupations
occupations_df = pres_merged_df['Occupation'].str.split(', ', expand=True)

# Create a list of presidents for each occupation
presidents_by_occupation = {}
for col in occupations_df.columns:
    for index, president in enumerate(occupations_df[col].dropna()):
        if president not in presidents_by_occupation:
            presidents_by_occupation[president] = []
        presidents_by_occupation[president].append(pres_merged_df['President_x'].iloc[index])

# Get the frequency of each occupation
occupation_counts = occupations_df.melt(value_name='Occupation').groupby('Occupation').size()

# Sort the occupations by frequency in descending order
occupation_counts = occupation_counts.sort_values(ascending=False)

# Create the bar chart
fig = px.bar(
    x=occupation_counts.index,
    y=occupation_counts.values,
    labels={'x': 'Occupation', 'y': 'Frequency'},
    title='Frequency of Jobs of U.S. Presidents',
    color=occupation_counts.index,  # Use different colors for each occupation
    hover_name=occupation_counts.index,  # Show occupation names in the tooltip
    hover_data={"Presidents": [", ".join(presidents_by_occupation[occupation]) for occupation in occupation_counts.index]},
)

# Customize the appearance of the chart
fig.update_layout(
    xaxis_title="Occupation",
    yaxis_title="Frequency",
    xaxis_tickangle=-45,
    hoverlabel=dict(bgcolor="white", font_size=12),
    template='plotly_dark',  # Set the plot template to a dark theme
    height = 600,
)

# Display the interactive plot
fig.show()


import pandas as pd
import plotly.graph_objects as go
from ipywidgets import interact, widgets

# Assuming you have a DataFrame called 'pres_merged_df' containing the data
# with columns: 'President_x' and 'Occupation'

# Filter out missing data
pres_merged_df = pres_merged_df.dropna(subset=['Occupation'])

# Create a dictionary to map presidents to their occupations
president_occupation_dict = dict(zip(pres_merged_df['President_x'], pres_merged_df['Occupation']))

# Function to plot the occupation value for a specific president
def plot_occupation(president_name):
    occupation = president_occupation_dict.get(president_name, 'Occupation data not available')

    # Create the plot
    fig = go.Figure()

    # Add a text annotation to display the occupation value
    fig.add_annotation(
        text=f"Occupation: <span style='color: #2b9434;'>{occupation}</span>",
        xref="paper",
        yref="paper",
        x=0.5,
        y=0.5,
        showarrow=False,
        font=dict(size=16),
        align='center',
    )

    # Update layout for better appearance
    fig.update_layout(
        title=f"Occupation of U.S. President - {president_name}",
        xaxis=dict(visible=False),
        yaxis=dict(visible=False),
        width=1400,
        height=400,
        template='plotly_dark',  # Use dark theme
        margin=dict(t=100),
    )

    # Show the plot
    fig.show()

# Get unique president names from the DataFrame
president_names = pres_merged_df['President_x'].unique()

# Create an interactive dropdown menu to select the president
interact(plot_occupation, president_name=widgets.Dropdown(options=president_names));


import pandas as pd
import plotly.express as px
from ipywidgets import interact, widgets

# Assuming you have a DataFrame called 'pres_merged_df' containing the data
# with columns: 'President_x', 'Party', and 'Occupation'

# Filter out missing data
pres_merged_df = pres_merged_df.dropna(subset=['Occupation', 'Party'])

# Function to split occupations and calculate the most frequent occupation for each party
def get_most_frequent_occupation(selected_party):
    # Filter DataFrame based on the selected party
    party_df = pres_merged_df[pres_merged_df['Party'] == selected_party]

    # Split occupations and create a list of all occupation tokens
    all_occupations = [occupation.strip() for occupations in party_df['Occupation'] for occupation in occupations.split(',')]

    # Count the occurrences of each occupation
    occupation_counts = pd.Series(all_occupations).value_counts()

    # Get the most frequent occupation
    most_frequent_occupation = occupation_counts.index[0]

    # Create the bar plot
    fig = px.bar(
        occupation_counts,
        x=occupation_counts.index,
        y=occupation_counts.values,
        labels={'x': 'Occupation', 'y': 'Frequency'},
        title=f"Most Frequent Occupation for {selected_party} Party",
        color=occupation_counts.index,
    )

    # Rotate x-axis labels for better readability
    fig.update_layout(xaxis_tickangle=-45)

    # Show the plot
    fig.show()

# Get unique political parties from the DataFrame
parties = pres_merged_df['Party'].unique()

# Create an interactive dropdown menu to select the party
interact(get_most_frequent_occupation, selected_party=widgets.Dropdown(options=parties));


import pandas as pd
import plotly.express as px

# Assuming you have a DataFrame called 'pres_merged_df' containing the data
# with columns: 'President_x' and 'Military Service'

# Filter out missing data
pres_merged_df = pres_merged_df.dropna(subset=['Military Service'])

# Split the military service data in each row and strip leading/trailing spaces
military_service_split = pres_merged_df['Military Service'].str.split(',').apply(lambda x: [service.strip() for service in x])

# Create a DataFrame to store the data for the TreeMap
data = pd.DataFrame(columns=['Service', 'President', 'Value'])

# Process the data to populate the DataFrame
for i, service_list in enumerate(military_service_split):
    for service in service_list:
        if service:
            data = data.append({'Service': service, 'President': pres_merged_df.iloc[i]['President_x'], 'Value': 1}, ignore_index=True)

# Create the TreeMap
fig = px.treemap(data, path=['Service', 'President'], values='Value')

# Update layout for better appearance
fig.update_layout(
    title="Military Service of U.S. Presidents - TreeMap",
    margin=dict(t=100),
    template='plotly_dark',  # Use dark theme
    height = 600,
)

# Show the TreeMap
fig.show()


import pandas as pd
import nltk
from wordcloud import WordCloud
import matplotlib.pyplot as plt

# Assuming you have a DataFrame called 'pres_merged_df' containing the data
# with columns: 'President_x' and 'Previous Office'

# Download the 'punkt' tokenizer
nltk.download('punkt')

# Filter out missing data
pres_merged_df = pres_merged_df.dropna(subset=['Previous Office'])

# Concatenate all the 'Previous Office' values into a single string
previous_office_text = ' '.join(pres_merged_df['Previous Office'])

# Split the text into individual words
words = nltk.word_tokenize(previous_office_text)

# Calculate the frequency of each word
word_freq = nltk.FreqDist(words)

# Get the most frequent words and their frequencies
most_common_words = word_freq.most_common(10)

# Create a dictionary to hold the most frequent words and their frequencies
wordcloud_data = dict(most_common_words)

# Create the Word Cloud with custom settings
wordcloud = WordCloud(
    width=1200,
    height=600,
    background_color='black',  # Set the background color to black
    colormap='viridis',  # Choose a color map for the Word Cloud
    contour_color='white',  # Set contour color for better visibility
    contour_width=2,  # Set contour width
    max_words=150,  # Set the maximum number of words in the Word Cloud
    prefer_horizontal=0.8,  # Set the ratio of horizontal to vertical words
).generate_from_frequencies(wordcloud_data)

# Display the Word Cloud using matplotlib
plt.figure(figsize=(12, 6))
plt.imshow(wordcloud, interpolation='bilinear')
plt.axis('off')
plt.title("Most Frequent Previous Offices of U.S. Presidents - Word Cloud", fontsize=20, color='white')
plt.show()

[nltk_data] Downloading package punkt to
[nltk_data]     C:\Users\User\AppData\Roaming\nltk_data...
[nltk_data]   Package punkt is already up-to-date!


import pandas as pd
import matplotlib.pyplot as plt
import matplotlib.image as mpimg
from wordcloud import WordCloud

# Assuming you have a DataFrame called 'pres_merged_df' containing the data
# with columns: 'President_x' and 'Previous Office'

# Concatenate all the 'Previous Office' values into a single string
previous_office_text = ' '.join(pres_merged_df['Previous Office'].dropna())

# Read the mask image
mask_img = mpimg.imread(r'C:\Users\User\Desktop\GitHub-projects\projects\Data-Dives-Projects-Unleashed\images\course1_1\png\fantasy-2506830_1280.jpg')

# Create a WordCloud object with the custom shape mask
wordcloud = WordCloud(
    width=1200,
    height=600,
    background_color='black',  # Set the background color to black
    colormap='tab20c',  # Choose a custom color map for the Word Cloud
    contour_color='white',  # Set contour color for better visibility
    contour_width=2,  # Set contour width
    max_words=150,  # Set the maximum number of words in the Word Cloud
    prefer_horizontal=0.8,  # Set the ratio of horizontal to vertical words
    mask=mask_img,  # Use the custom mask for the Word Cloud
).generate(previous_office_text)

# Display the Word Cloud using matplotlib
plt.figure(figsize=(24, 12))
plt.imshow(wordcloud, interpolation='bilinear')
plt.axis('off')
plt.title("Previous Offices of U.S. Presidents - Word Cloud", fontsize=20, color='white')
plt.show()


import pandas as pd
import plotly.graph_objects as go

# Assuming you have a DataFrame called 'pres_merged_df' containing the data
# with columns: 'President_x' and 'Previous Office'

# Filter out missing data
pres_merged_df = pres_merged_df.dropna(subset=['Previous Office'])

# Create a DataFrame to store the frequency of each office
office_counts = pres_merged_df['Previous Office'].value_counts().reset_index()
office_counts.columns = ['Previous Office', 'Count']

# Create a Sunburst Chart
fig = go.Figure(go.Sunburst(
    labels=office_counts['Previous Office'],
    parents=[''] * len(office_counts),  # Empty string as parent for all categories
    values=office_counts['Count'],
))

# Update the layout for better appearance
fig.update_layout(
    title='Previous Offices of U.S. Presidents - Sunburst Chart',
    margin=dict(t=50),
    height=800,
    uniformtext=dict(minsize=12, mode='hide'),
)

# Show the chart
fig.show()


import pandas as pd
from ipywidgets import interact, widgets

# Assuming you have a DataFrame called 'pres_merged_df' containing the data
# with a column named 'Economy'

# Function to display the economy data for a specific president
def display_economy_data(president_name):
    economy_data = pres_merged_df.loc[pres_merged_df['President_x'] == president_name, 'Economy'].values
    if len(economy_data) == 0:
        economy_data = ['Economy data not available']
    else:
        # Split the economy data based on commas and create a list
        economy_data = [item.strip() for data in economy_data for item in data.split(',')]
    
    # Create a widget to display the economy data
    economy_widget = widgets.HTML(value='<br>'.join(economy_data))
    
    # Set the layout and style of the widget
    economy_widget.layout.overflow_x = 'hidden'
    economy_widget.layout.max_height = '500px'
    economy_widget.layout.overflow_y = 'auto'
    economy_widget.layout.border = '2px solid #ccc'
    economy_widget.layout.border_radius = '5px'
    economy_widget.layout.padding = '10px'
    economy_widget.layout.margin = '10px'
    economy_widget.layout.background = '#f9f9f9'
    
    # Display the widget
    display(economy_widget)

# Get unique president names from the DataFrame
president_names = pres_merged_df['President_x'].unique()

# Create an interactive dropdown menu to select the president
interact(display_economy_data, president_name=widgets.Dropdown(options=president_names));


import pandas as pd
from wordcloud import WordCloud
import matplotlib.pyplot as plt

# Assuming you have a DataFrame called 'pres_merged_df' containing the data
# with a column named 'Foreign Affairs'

# Concatenate all the 'Foreign Affairs' values into a single string
foreign_affairs_text = ' '.join(pres_merged_df['Foreign Affairs'].dropna())

# Create the Word Cloud with custom settings
wordcloud = WordCloud(
    width=1200,
    height=600,
    background_color='white',  # Set the background color to white
    colormap='tab20',  # Choose a custom color map for the Word Cloud
    contour_color='black',  # Set contour color for better visibility
    contour_width=2,  # Set contour width
    max_words=150,  # Set the maximum number of words in the Word Cloud
    prefer_horizontal=0.8,  # Set the ratio of horizontal to vertical words
).generate(foreign_affairs_text)

# Display the Word Cloud using matplotlib
plt.figure(figsize=(24, 12))
plt.imshow(wordcloud, interpolation='bilinear')
plt.axis('off')
plt.title("Foreign Affairs of U.S. Presidents - Word Cloud", fontsize=16, color='black')
plt.show()


import pandas as pd
import plotly.graph_objects as go
import random
from collections import Counter
from nltk.corpus import stopwords
import nltk
nltk.download('stopwords')

# Get the 'Foreign Affairs' text
foreign_affairs_text = ' '.join(pres_merged_df['Foreign Affairs'].dropna())

# Preprocess the text (You may need to customize this based on your data)
import string
from nltk.corpus import stopwords
from nltk.tokenize import word_tokenize

def preprocess_text(text):
    # Remove punctuation and convert to lowercase
    text = text.translate(str.maketrans('', '', string.punctuation)).lower()
    # Tokenize the text
    words = word_tokenize(text)
    # Remove stopwords
    stop_words = set(stopwords.words('english'))
    words = [word for word in words if word not in stop_words]
    return words

# Tokenize and preprocess the text
words = preprocess_text(foreign_affairs_text)

# Calculate word frequencies
word_freq = Counter(words)

# Create a DataFrame to store the word frequencies
word_freq_df = pd.DataFrame(word_freq.items(), columns=['Word', 'Frequency'])

# Sort the DataFrame by frequency in descending order
word_freq_df = word_freq_df.sort_values(by='Frequency', ascending=False)

# Create the Word Scatter Plot
fig = px.scatter(
    word_freq_df,
    x='Frequency',
    y='Frequency',
    text='Word',
    labels={'Frequency': 'Word Frequency'},
    title='Word Scatter Plot - Foreign Affairs',
    hover_name='Word',
    hover_data={'Frequency': True},
)

# Customize the appearance of the plot
fig.update_traces(textposition='top center', textfont_size=12)

fig.update_layout(height=600)
# Show the plot
fig.show()

[nltk_data] Downloading package stopwords to
[nltk_data]     C:\Users\User\AppData\Roaming\nltk_data...
[nltk_data]   Package stopwords is already up-to-date!


import pandas as pd
from ipywidgets import interact, widgets
import re

# Assuming you have a DataFrame called 'pres_merged_df' containing the data
# with a column named 'Foreign Affairs'

# Function to display the 'Foreign Affairs' data for a specific president
def display_foreign_affairs_data(president_name):
    foreign_affairs_data = pres_merged_df.loc[pres_merged_df['President_x'] == president_name, 'Foreign Affairs'].values
    if len(foreign_affairs_data) == 0:
        foreign_affairs_data = ['Foreign Affairs data not available']
    else:
        # Use regex to extract text between square brackets and split the text based on commas
        foreign_affairs_data = [item.strip() for data in foreign_affairs_data for item in re.findall(r'\[([^]]+)\]', data)[0].split(',')]

    # Remove empty strings and quotes from the list
    foreign_affairs_data = [item.replace("'", "").replace('"', '') for item in foreign_affairs_data if item]

    # Create an ordered list of the 'Foreign Affairs' data
    list_html = '<ol style="list-style-position: inside;">'
    for item in foreign_affairs_data:
        list_html += f'<li>{item}</li>'
    list_html += '</ol>'

    # Create a widget to display the 'Foreign Affairs' data as an ordered list
    foreign_affairs_widget = widgets.HTML(value=list_html)

    # Set the layout and style of the widget
    foreign_affairs_widget.layout.overflow_x = 'hidden'
    foreign_affairs_widget.layout.max_height = '500px'
    foreign_affairs_widget.layout.overflow_y = 'auto'
    foreign_affairs_widget.layout.border = '2px solid #ccc'
    foreign_affairs_widget.layout.border_radius = '5px'
    foreign_affairs_widget.layout.padding = '10px'
    foreign_affairs_widget.layout.margin = '10px'
    foreign_affairs_widget.layout.background = '#f9f9f9'

    # Display the widget
    display(foreign_affairs_widget)

# Get unique president names from the DataFrame
president_names = pres_merged_df['President_x'].unique()

# Create an interactive dropdown menu to select the president
interact(display_foreign_affairs_data, president_name=widgets.Dropdown(options=president_names));


import pandas as pd
from ipywidgets import interact, widgets, HTML
from ipywidgets.embed import embed_minimal_html
import re

# Assuming you have a DataFrame called 'pres_merged_df' containing the data
# with a column named 'Foreign Affairs'

# Function to display the 'Foreign Affairs' data for a specific president
def display_foreign_affairs_data(president_name):
    foreign_affairs_data = pres_merged_df.loc[pres_merged_df['President_x'] == president_name, 'Foreign Affairs'].values
    if len(foreign_affairs_data) == 0:
        foreign_affairs_data = ['Foreign Affairs data not available']
    else:
        # Use regex to extract text between square brackets and split the text based on commas
        foreign_affairs_data = [item.strip() for data in foreign_affairs_data for item in re.findall(r'\[([^]]+)\]', data)[0].split(',')]

    # Remove empty strings and quotes from the list
    foreign_affairs_data = [item.replace("'", "").replace('"', '') for item in foreign_affairs_data if item]

    # Create an ordered list of the 'Foreign Affairs' data
    list_html = '<ol style="list-style-position: inside;">'
    for item in foreign_affairs_data:
        list_html += f'<li>{item}</li>'
    list_html += '</ol>'

    # Create a widget to display the 'Foreign Affairs' data as an ordered list
    foreign_affairs_widget = widgets.HTML(value=list_html)

    # Set the layout and style of the widget
    foreign_affairs_widget.layout.overflow_x = 'hidden'
    foreign_affairs_widget.layout.max_height = '500px'
    foreign_affairs_widget.layout.overflow_y = 'auto'
    foreign_affairs_widget.layout.border = '2px solid #ccc'
    foreign_affairs_widget.layout.border_radius = '5px'
    foreign_affairs_widget.layout.padding = '10px'
    foreign_affairs_widget.layout.margin = '10px'
    foreign_affairs_widget.layout.background = '#f9f9f9'

    # Display the widget
    display(foreign_affairs_widget)

    # Save the interactive widget to an HTML file
    embed_minimal_html('interactive_foreign_affairs_widget.html', views=[foreign_affairs_widget], title='Foreign Affairs Widget')

# Get unique president names from the DataFrame
president_names = pres_merged_df['President_x'].unique()

# Create an interactive dropdown menu to select the president
interact(display_foreign_affairs_data, president_name=widgets.Dropdown(options=president_names));


import pandas as pd
import ipywidgets as widgets
import re

# Assuming you have a DataFrame called 'pres_merged_df' containing the data
# with columns: 'President_x', 'Economy', 'Foreign Affairs', 'Military Activity', 'Other Events', and 'Legacy'

# Function to split data by commas and display the data for a specific president
def display_president_data(president_name):
    president_data = pres_merged_df.loc[pres_merged_df['President_x'] == president_name]
    
    # Function to split data by commas and create an ordered list
    def create_ordered_list(data_column):
        data_list = president_data[data_column].dropna().apply(lambda x: re.sub(r"[\[\]\"]", "", x)).tolist()
        data_list = [item.strip() for data in data_list for item in data.split(',')]
        data_list = [re.sub(r"[\"']+", "", item) for item in data_list]
        data_list = [f"{i+1}. {item}" for i, item in enumerate(data_list)]
        return data_list

    # Create ordered lists for each column's data
    economy_list = create_ordered_list('Economy')
    foreign_affairs_list = create_ordered_list('Foreign Affairs')
    military_activity_list = create_ordered_list('Military Activity')
    other_events_list = create_ordered_list('Other Events')
    legacy_list = create_ordered_list('Legacy')
    
    # Display the data in an interactive widget
    economy_widget = widgets.HTML(value=f"<b>Economy:</b><br>{'<br>'.join(economy_list)}")
    foreign_affairs_widget = widgets.HTML(value=f"<b>Foreign Affairs:</b><br>{'<br>'.join(foreign_affairs_list)}")
    military_activity_widget = widgets.HTML(value=f"<b>Military Activity:</b><br>{'<br>'.join(military_activity_list)}")
    other_events_widget = widgets.HTML(value=f"<b>Other Events:</b><br>{'<br>'.join(other_events_list)}")
    legacy_widget = widgets.HTML(value=f"<b>Legacy:</b><br>{'<br>'.join(legacy_list)}")
    
    # Create a tab widget to organize the data
    tab_contents = [economy_widget, foreign_affairs_widget, military_activity_widget, other_events_widget, legacy_widget]
    tab_titles = ['Economy', 'Foreign Affairs', 'Military Activity', 'Other Events', 'Legacy']
    tab = widgets.Tab()
    tab.children = tab_contents
    for i in range(len(tab_titles)):
        tab.set_title(i, tab_titles[i])
    
    # Display the tab widget
    display(tab)

# Get unique president names from the DataFrame
president_names = pres_merged_df['President_x'].unique()

# Create an interactive dropdown menu to select the president
interact(display_president_data, president_name=widgets.Dropdown(options=president_names));


# understand Economy, Foreign Affairs, Military Activity, Other Events, Legacy
for i in range(0,46):
    print(pres_merged_df['Other Events'].loc[i])
    print()

['1791 Bill of Rights', '1792 Post Office founded.', '1792, 1796 Kentucky  & Tennessee joined the Union']

['1798 Alien & Sedition Act to silence critics; unpopular', '1800 Capital relocated to Washington DC', '1801 Nominated John Marshall chief justice of  U.S.']

['1803 The Louisiana purchase', '1804 12th Amendment changed Presidential election', '1804-06 Authorized Louis & Clark expedition']

['1811 Cumberland Road construction starts (first National Road)', '1817 Veto on  Bonus Bill  for funding States improvements']

['1819 Florida ceded to US', "1820 Missouri Compromise Slavery forbidden abv 36° 30'", '1820 In the election he received every electoral vote except one.']

[' Accused for "corrupt bargain" to obtain Clay\'s support in election', '1828 Baltimore/Ohio railroad']

['1830 Indian Removal Act', "1832 South Carolina's nullification crisis over taxes", '1835 "The Trail of Tears". Cherokees forced to move.']

['1838 "The Trail of Tears". Indians’ relocation, 4000 die', '1839 US vs. The Amistad: symbolic against slavery']

['1841 Delivered the longest inaugural address (105 min)', '1841 Contracted pneumonia and died in the White House one month later.']

['1841 His cabinet resigned after he vetoed banking bills', '1844 USS Princeton disaster. 8  died in Potomac,', '1845 Texas annexed followed by war with Mexico']

['1846 A large crack in the Liberty Bell.', '1848 California Gold rush']

[' The question of extending slavery to the new territories dominated', '1846 Did not approve the "Compromise of 1850"']

['1850 Compromise of 1850 and Fugitive Slave Act.']

['1853 Gadsden Purchase. Land from Mexico.', '1854 Kansas-Nebraska Act. Slavery Debate reheated.', ' "border ruffians" and "jayhawkers" clash in Kansas']

['1857 Dred Scott decision: States can decide on slavery', '1857 Mormons challenged federal authority in Utah.', '1860 Sth Carolina seceded. 7  states followed.']

['1863 Emancipation Proclamation, freeing slaves', '1863 Gettysburg Address', '1865 Assassinated by John Wilkes Booth']

['1865 Amnesty', '1867 Reconstruction Act & Office Tenure Act by Congress', ' Nebraska in the union', '1867 Purchase of Alaska', '1868 Impeachment']

['1871 Civil Service', '1870-71 Enforcement Acts broke Ku Klux Klan', '1875 Civil Rights Act', ' Scandals: Credit Mobilier, Tweed Ring, Whiskey Ring']

['1877 Reconstruction end. Army withdrew from the South', '1877 Railroad strikes and use of troops', '1877 Desert Land Act']

['1881 On July 2, he was shot by Charles Julius Guiteau.', '1881 Garfield died of blood poisoning on September 19.']

['1883 Pendleton Act: Civil hiring on merit']

['1886 Statue of Liberty', ' Curtailed largess of war veterans pensions', '1887 Anti-Polygamy Act', '1887 Dawes Severalty Act - destroys Indian governments']

['1889 Opening of Oklahoma to 20,000 settlers', '1889-90 6 states admitted to the Union', '1891 Forest Reserve Act; Forest reserves are public.']

['1893 Pullman strike.']

['1898 Yellow Journalism (Hyped Maine)', '1898 Hawaii annexed', '1901 On Sep 6, he was shot by an anarchist in Buffalo and died 8 days later.']

[' Conservation becomes an issue. Creation of National parks & forests', '1906 Pure Food & Drug Act - Meat Inspection Act: New Safety standards']

[' Record antitrust suits', '1912 New states: Arizona & New Mexico.', '1912 US dept. of Commerce created']

['1916 Child labor curtailed', '1916 Federal Farm Loan Act; cheap loans to farmers', '1920 Prohibition', '1920 19th Amendment, Women win the right to  vote']

['1921 Federal Highway Act  - the age of the "motor car"', '1922 Great Railway strike', ' Bureau of Veterans Affairs', ' Teapot Dome scandal and many others']

['1924 Immigration Act limits immigrants from South & East Europe', '1924 Snyder Act-Indians get citizenship', '1927 Mississippi flood']

['1932 Reconstruction Finance Corporation to provide business loans.', '1932 The "Bonus Army" incident. Veterans were killed.']

['1933 First 100 days legislation frenzy', '1933 1st New Deal: acts on relief, recovery, reform', '1935 2nd New Deal: WPA, Social Security,Labor support']

['1945 Fair Deal: health care, civil rights etc.', '1947 Pres. Succession Act', '1947 CIA established.', '1951 Dismissal of Gen. Douglas MacArthur']

[' Alaska and Hawaii admitted as states', '1957 Sent Troops to Little Rock to enforce integration', '1958 NASA established.', '1960 Civil Rights']

['1961 Peace Corps program', '1961 "Moon race" starts', '1963 "Washington March"', '1963 Assassinated In Dallas by Lee Harvey Oswald']

['1964 The Civil Rights Act', '1964 Great Society & War on Poverty programs', '1963-65 Miranda case', ' Urban riots / antiwar riots', '1968 M. Luther King killed']

['1969 Moon landing', '1970 Environment Act', '1973 Spiro Agnew resigned', '1973 Watergate scandal', '1974 Resigned']

['1974 Granted a pardon to  Nixon.', '1975 Airlift of 237,000 Vietnamese refugees']

[' Pardoned  Vietnam War draft evaders', ' Energy Department', ' Boycott of 1980 Olympics']

['1981 Assassination attempt by John W. Hinkley,', '1981 Fired 11,345 striking air traffic controllers.', '1986 War on Drugs']

['1990 Americans with Disabilities Act', '1990 Immigration Act; result: increase of legal immigration 40%']

["1993 “Don't ask, don't tell”- gays in the military.", ' Monica Lewinsky scandal & Impeachment']

['2001 9/11', '2001 Patriot Act', '2002 “no child left behind” law to improve education', '2005 Hurricane Katrina']

['2010 Healthcare reform: Affordable Care Act (Obamacare)', "2010 End of the “Don't ask, don't tell policy” for LBGT in the military", '2012 Same sex couples now have the right to be married.']

['2020 Covid-19 pandemic', ' Impeached twice', '2021 US Capitol was stormed by Trump supporters.']

['Biden pledged to double climate funding to developing countries by 2024']


import pandas as pd
import plotly.graph_objects as go
import re

# Assuming you have a DataFrame called 'pres_merged_df' containing the data
# with columns: 'President_x' and 'Party'

# Filter out NaN (float) values from the 'President_x' column
pres_merged_df = pres_merged_df.dropna(subset=['President_x'])

# Convert the 'President_x' column to string type
pres_merged_df['President_x'] = pres_merged_df['President_x'].astype(str)

# Split the names of the presidents into individual words using regex
pres_merged_df['President_x'] = pres_merged_df['President_x'].apply(lambda x: re.findall(r'\w+', x))

# Flatten the list of names
all_names = [name for sublist in pres_merged_df['President_x'] for name in sublist]

# Count the frequency of each name
name_freq = pd.Series(all_names).value_counts()

# Create a DataFrame to store president names and their frequencies
president_data = pd.DataFrame({'Name': name_freq.index, 'Frequency': name_freq.values})

# Filter out names with frequency less than 3
president_data = president_data[president_data['Frequency'] >= 3]

# Create a new column in the DataFrame to store party information
president_data['Party'] = None

# Function to get the party for each president name
def get_party(name):
    party = pres_merged_df.loc[pres_merged_df['President_x'].apply(lambda x: name in x), 'Party'].values
    return party[0] if len(party) > 0 else None

# Apply the function to get the party information for each president name
president_data['Party'] = president_data['Name'].apply(get_party)

# Check if the president_data DataFrame is not empty
if not president_data.empty:
    # Calculate the percentage of each party for each president name
    party_percentages = []
    for name, freq in zip(president_data['Name'], president_data['Frequency']):
        party_counts = pres_merged_df.loc[pres_merged_df['President_x'].apply(lambda x: name in x), 'Party'].value_counts()
        party_percentage = [f"{party}: {count} ({(count / freq * 100):.1f}%)" for party, count in party_counts.items()]
        party_percentages.append(', '.join(party_percentage))

    # Create the interactive horizontal bar plot using Plotly
    fig = go.Figure()

    fig.add_trace(
        go.Bar(
            x=president_data['Frequency'],
            y=president_data['Name'],
            name='Presidents',
            orientation='h',
            hovertext=party_percentages
        )
    )

    # Update layout for better appearance
    fig.update_layout(
        title="Frequency of U.S. President Names with Party Information",
        xaxis_title="Frequency",
        yaxis_title="President Names",
        hovermode='closest',
        barmode='stack',
        showlegend=False,  # No need to show the legend as there's only one trace
    )

    # Show the plot
    fig.show()
else:
    print("No data available for the selected condition.")


# Merge pres_df_1, pres_df_3, and pres_df_4 based on the column 'President'
pres_merged_df = pres_df_1.merge(pres_df_4, left_index=True, right_index=True)


import pandas as pd
import matplotlib.pyplot as plt


# Calculate the age at marriage for the First Lady
pres_df_2['Age at Marriage, First Lady'] = (pres_df_2['Date of Marriage'] - pres_df_2['Date of Born, First Lady']).dt.days // 365

# Plot the distribution of age at marriage
plt.figure(figsize=(20, 12))
plt.hist(pres_df_2['Age at Marriage, First Lady'], bins=20, edgecolor='black', alpha=0.7)

# Calculate and plot the median, mean, and mode
median_age = pres_df_2['Age at Marriage, First Lady'].median()
mean_age = pres_df_2['Age at Marriage, First Lady'].mean()
mode_age = pres_df_2['Age at Marriage, First Lady'].mode().values[0]

plt.axvline(median_age, color='red', linestyle='dashed', linewidth=2, label=f'Median Age: {median_age:.1f}')
plt.axvline(mean_age, color='green', linestyle='dashed', linewidth=2, label=f'Mean Age: {mean_age:.1f}')
plt.axvline(mode_age, color='blue', linestyle='dashed', linewidth=2, label=f'Mode Age: {mode_age:.1f}')

plt.xlabel('Age at Marriage of First Lady')
plt.ylabel('Frequency')
plt.title('Distribution of Age at Marriage of First Ladies')
plt.legend()
plt.grid(True)
plt.show()


import plotly.graph_objects as go

# Assuming you have a DataFrame called 'pres_df_2' containing the data
# with columns: 'First Lady Name', 'Age at Marriage, First Lady', and 'President'

# Filter out rows with missing values in 'Age at Marriage, First Lady' column
pres_df_2 = pres_df_2.dropna(subset=['Age at Marriage, First Lady'])

# Create the horizontal bar chart using Plotly
fig = go.Figure()

# Add the bar data to the figure
fig.add_trace(go.Bar(
    y=pres_df_2['First Lady Name'],
    x=pres_df_2['Age at Marriage, First Lady'],
    orientation='h',
    text=pres_df_2.apply(lambda row: f"President: {row['President']} <br> First Lady: {row['First Lady Name']} <br> Age at Marriage: {row['Age at Marriage, First Lady']}", axis=1),
    hoverinfo='text',  # Show custom hover text
    marker=dict(color='skyblue'),
    opacity=0.8
))

# Update layout for better appearance
fig.update_layout(
    title="Age at Marriage, First Lady",
    xaxis_title="Age at Marriage (years)",
    yaxis_title="First Lady Name",
    showlegend=False,
    bargap=0.1,
    height=1400
)

# Show the plot
fig.show()


import pandas as pd
import plotly.express as px

# Assuming you have a DataFrame called 'pres_df_3' containing the data
# with columns: 'President', 'height_cm', 'weight_kg', 'body_mass_index', and 'political_party'

# Filter out NaN (missing) values
pres_df_3 = pres_df_3.dropna(subset=['height_cm', 'weight_kg', 'body_mass_index', 'political_party'])

# Create a dictionary to map political parties to colors
party_colors = {
    'Democratic': 'blue',
    'Republican': 'red',
    # Add more parties and their corresponding colors here
}

# Map party names to colors using the dictionary
pres_df_3['Party Color'] = pres_df_3['political_party'].map(party_colors)

# Calculate the Body Mass Index (BMI) range for each person
def calculate_bmi_range(bmi):
    if bmi < 18.5:
        return 'Underweight'
    elif 18.5 <= bmi < 24.9:
        return 'Normal Weight'
    elif 25 <= bmi < 29.9:
        return 'Overweight'
    else:
        return 'Obese'

#pres_df_3['body_mass_index_range'] = pres_df_3['body_mass_index'].apply(calculate_bmi_range)

# Create the hover text with the desired information
hover_text = pres_df_3.apply(
    lambda row: f"President: {row['President']}<br>"
                f"Height: {row['height_cm']} cm<br>"
                f"Weight: {row['weight_kg']} kg<br>"
                f"Party: {row['political_party']}<br>"
                f"Body Mass Index: {row['body_mass_index']}<br>"
                f"Body Mass Index Range: {row['body_mass_index_range']}",
    axis=1
)

# Create the scatter plot
fig = px.scatter(
    pres_df_3,
    x='height_cm',
    y='weight_kg',
    size='body_mass_index',
    color='political_party',
    color_discrete_map=party_colors,  # Assign colors to parties
    hover_name='President',  # Display the President name on hover
    custom_data=['height_cm', 'weight_kg', 'body_mass_index', 'political_party', 'body_mass_index_range'],
    title="Height vs. Weight with Body Mass Index and Political Party",
    labels={'height_cm': 'Height (cm)', 'weight_kg': 'Weight (kg)'},
)

# Update hover information
fig.update_traces(
    hovertemplate="<br>".join([
        "President: %{hovertext}",
        "Height: %{customdata[0]} cm",
        "Weight: %{customdata[1]} kg",
        "Party: %{customdata[3]}",
        "Body Mass Index: %{customdata[2]}",
        "Body Mass Index Range: %{customdata[4]}"
    ])
)

# Update the layout for better appearance
fig.update_layout(
    autosize=False,  # Turn off automatic sizing
    width=1500,       # Set the width of the plot
    height=700,      # Set the height of the plot
)

# Show the plot
fig.show()


import pandas as pd
import plotly.graph_objects as go

# Assuming you have a DataFrame called 'pres_df_3' containing the data
# with columns: 'birth_state' and 'political_party'

# Calculate the count of presidents born in each state
state_counts = pres_df_3['birth_state'].value_counts()

# Create a new DataFrame to store the hover text and color information
hover_text_data = pd.DataFrame(columns=['State', 'Presidents', 'Party Percentage', 'Color'])

# Define party colors
party_colors = {'Democrat': 'blue', 'Republican': 'red'}

# Iterate over each state and calculate the hover text and color information
for state in state_counts.index:
    presidents_in_state = pres_df_3[pres_df_3['birth_state'] == state]['President']
    party_percentage = pres_df_3[pres_df_3['birth_state'] == state]['political_party'].value_counts(normalize=True)
    party_percentage_text = '<br>'.join([f"{party}: {percentage:.2f}" for party, percentage in party_percentage.items()])
    max_party = party_percentage.idxmax()
    color = party_colors.get(max_party, 'green')
    hover_text_data = hover_text_data.append({'State': state, 'Presidents': ', '.join(presidents_in_state), 'Party Percentage': party_percentage_text, 'Color': color}, ignore_index=True)

# Create the bar chart using Plotly
fig = go.Figure()

fig.add_trace(
    go.Bar(
        x=state_counts.index,
        y=state_counts.values,
        hovertext=[f"Presidents: {presidents}<br>Party Percentage:<br>{party_percentage}" for presidents, party_percentage in zip(hover_text_data['Presidents'], hover_text_data['Party Percentage'])],
        hoverinfo='text',
        marker=dict(color=hover_text_data['Color']),
        name='Party',  # Legend name for the colors
    )
)

# Update layout for better appearance
fig.update_layout(
    title="Number of Presidents Born in Each State",
    xaxis_title="State",
    yaxis_title="Number of Presidents",
    hovermode='closest',
    barmode='stack',
    showlegend=True,  # Show the legend for the colors
)

# Show the plot
fig.show()


import pandas as pd
import folium
from folium import Choropleth, GeoJson
import geopandas as gpd

# Assuming you have a DataFrame called 'pres_df_3' containing the data
# with a column named 'birth_state' containing the names of states where presidents were born

# Calculate the most common states where presidents were born
most_common_states = pres_df_3['birth_state'].value_counts()

# Shapefile location
states_shapefile = r'C:\Users\User\Desktop\GitHub-projects\projects\Data-Dives-Projects-Unleashed\Notebooks\course1\maps\ne_10m_admin_1_states_provinces.shp'

# Read the shapefile using geopandas with the correct encoding
gdf = gpd.read_file(states_shapefile, encoding='latin1')

# Merge the GeoDataFrame with the most common states data
merged_gdf = gdf.merge(most_common_states, left_on='name', right_index=True)

# Create a map centered on the U.S. using Folium
map_us = folium.Map(location=[37.0902, -95.7129], zoom_start=4)

# Add the choropleth map layer to the map
Choropleth(
    geo_data=merged_gdf,
    name='choropleth',
    data=most_common_states.reset_index(),
    columns=['index', 'birth_state'],  # Column names for the data
    key_on='feature.properties.name',  # Key for the GeoJSON data
    fill_color='YlGnBu',  # Color palette for the map
    fill_opacity=0.7,
    line_opacity=0.2,
    legend_name='Most Common States of President Births',
).add_to(map_us)

# Add state names and birth counts to the map as popups
for _, row in merged_gdf.iterrows():
    folium.Marker(
        location=[row.geometry.centroid.y, row.geometry.centroid.x],
        popup=f"{row['name']}: {row['birth_state']} Presidents Born",
        icon=folium.Icon(color='red', icon='info-sign')
    ).add_to(map_us)

# Display the map
map_us


import pandas as pd
import plotly.graph_objects as go

# Assuming you have a DataFrame called 'pres_df_3' containing the data
# with columns 'President', 'corrected_iq', and 'political_party'

# Sort the DataFrame by 'corrected_iq' in descending order
pres_df_3_sorted = pres_df_3.sort_values(by='corrected_iq', ascending=False)

# Create a dictionary to map political parties to colors
party_colors = {
    'Unaffiliated': 'gray',
    'Federalist': 'darkblue',
    'Democratic-Republican': 'green',
    'Democrat': 'blue',
    'Whig': 'purple',
    'Republican': 'red',
    'National Union': 'orange',
}

# Create the horizontal bar chart using Plotly
fig = go.Figure()

fig.add_trace(go.Bar(
    x=pres_df_3_sorted['corrected_iq'],
    y=pres_df_3_sorted['President'],
    text=pres_df_3_sorted.apply(
        lambda row: f"{row['President']}<br>IQ: {row['corrected_iq']}<br>Party: {row['political_party']}",
        axis=1
    ),
    hoverinfo='text',
    marker=dict(color=pres_df_3_sorted['political_party'].map(party_colors).fillna('#AAAAAA')),
    orientation='h',
))

# Update layout for better appearance
fig.update_layout(
    title="IQ Scores of U.S. Presidents from Most Intelligent to Least",
    title_font=dict(size=24),
    xaxis=dict(title="Corrected IQ"),
    yaxis=dict(title="President"),
    showlegend=False,
    width = 1400,
    height = 1700,
)

# Show the plot
fig.show()


import pandas as pd
import plotly.express as px

# Assuming you have a DataFrame called 'pres_df_3' containing the data
# with a column 'corrected_iq' representing IQ scores of presidents

# Create the interactive box plot using Plotly
fig = px.box(
    pres_df_3,
    y='corrected_iq',
    title="IQ Scores of U.S. Presidents",
    labels={'corrected_iq': 'IQ Score'},
    hover_data={'corrected_iq': True},  # Display the IQ score on hover
)

# Update layout for better appearance
fig.update_layout(
    yaxis_title="IQ Score",
    boxmode='group',  # Display multiple boxes side by side
    boxgroupgap=0.3,  # Gap between boxes in the same group
    showlegend=False,  # Hide the legend
)

# Show the plot
fig.show()


import pandas as pd
import plotly.graph_objects as go

# Assuming you have a DataFrame called 'pres_df_3' containing the data
# with a column 'corrected_iq' representing IQ scores of presidents

# Create the radar chart using Plotly
fig = go.Figure()

fig.add_trace(go.Scatterpolar(
    r=pres_df_3['corrected_iq'],
    theta=pres_df_3['President'],
    fill='toself',
    hovertext=pres_df_3['corrected_iq'],
    hoverinfo='text',
    line=dict(color='blue')
))

# Update layout for better appearance
fig.update_layout(
    polar=dict(
        radialaxis=dict(
            visible=True,
            range=[min(pres_df_3['corrected_iq']), max(pres_df_3['corrected_iq'])],
        ),
    ),
    showlegend=False,  # Hide the legend
    title="IQ Scores of U.S. Presidents by Cognitive Abilities",
    width = 1400,
    height = 1400,
)

# Show the plot
fig.show()


import pandas as pd
import plotly.graph_objects as go

# Assuming you have a DataFrame called 'pres_df_3' containing the data
# with a column 'corrected_iq' representing IQ scores of presidents

# Create the radar chart using Plotly
fig = go.Figure()

for i, (_, row) in enumerate(pres_df_3.iterrows()):
    fig.add_trace(go.Scatterpolar(
        r=[row['corrected_iq']],  # Use a list with the corrected_iq value as the only element
        theta=[row['President']],
        fill='toself',
        hovertext=f"{row['President']}<br>IQ: {row['corrected_iq']}<br>Party: {row['political_party']}",
        hoverinfo='text',
        line=dict(color=party_colors.get(row['political_party'], '#AAAAAA'), width=2),
        name=row['President']
    ))

# Update layout for better appearance
fig.update_layout(
    polar=dict(
        radialaxis=dict(
            visible=True,
            range=[0, 200],
        ),
    ),
    showlegend=False,
    legend=dict(
        orientation="h",
        yanchor="bottom",
        y=1.02,
        xanchor="right",
        x=1,
    ),
    title="IQ Scores of U.S. Presidents by Cognitive Abilities and Political Party",
    title_font=dict(size=24),
    annotations=[],  # Remove any annotations in the layout
    width = 1400,
    height = 1400,
)

# Show the plot
fig.show()

	#	President	Born	Age atstart of presidency	Age atend of presidency	Post-presidencytimespan	Died	Age
0	1	George Washington	Feb 22, 1732[a]	57 years, 67 daysApr 30, 1789	65 years, 10 daysMar 4, 1797	2 years, 285 days	Dec 14, 1799	67 years, 295 days
1	2	John Adams	Oct 30, 1735[a]	61 years, 125 daysMar 4, 1797	65 years, 125 daysMar 4, 1801	25 years, 122 days	Jul 4, 1826	90 years, 247 days
2	3	Thomas Jefferson	Apr 13, 1743[a]	57 years, 325 daysMar 4, 1801	65 years, 325 daysMar 4, 1809	17 years, 122 days	Jul 4, 1826	83 years, 82 days
3	4	James Madison	Mar 16, 1751[a]	57 years, 353 daysMar 4, 1809	65 years, 353 daysMar 4, 1817	19 years, 116 days	Jun 28, 1836	85 years, 104 days
4	5	James Monroe	Apr 28, 1758	58 years, 310 daysMar 4, 1817	66 years, 310 daysMar 4, 1825	6 years, 122 days	Jul 4, 1831	73 years, 67 days

	#	President	Born	Age atstart of presidency	Age atend of presidency	Post-presidencytimespan	Died	Age
0	1	George Washington	Feb 22, 1732[a]	57 years, 67 daysApr 30, 1789	65 years, 10 daysMar 4, 1797	2 years, 285 days	Dec 14, 1799	67 years, 295 days
1	2	John Adams	Oct 30, 1735[a]	61 years, 125 daysMar 4, 1797	65 years, 125 daysMar 4, 1801	25 years, 122 days	Jul 4, 1826	90 years, 247 days
2	3	Thomas Jefferson	Apr 13, 1743[a]	57 years, 325 daysMar 4, 1801	65 years, 325 daysMar 4, 1809	17 years, 122 days	Jul 4, 1826	83 years, 82 days
3	4	James Madison	Mar 16, 1751[a]	57 years, 353 daysMar 4, 1809	65 years, 353 daysMar 4, 1817	19 years, 116 days	Jun 28, 1836	85 years, 104 days
4	5	James Monroe	Apr 28, 1758	58 years, 310 daysMar 4, 1817	66 years, 310 daysMar 4, 1825	6 years, 122 days	Jul 4, 1831	73 years, 67 days

	Unnamed: 0	relation	name	president	born	death	age_of_death	marriage_date
0	0	Husband	Martha Dandridge	George Washington	June 13, 1731	May 22, 1802	70.0	January 6, 1759
1	1	Husband	Abigail Smith	John Adams	November 22, 1744	October 28, 1818	73.0	October 25, 1764
2	2	Father	Martha Jefferson	Thomas Jefferson	September 27, 1772	October 10, 1836	64.0	NaN
3	3	Husband	Dolley Payne	James Madison	May 20, 1768	July 12, 1849	81.0	September 14, 1794
4	4	Husband	Elizabeth Kortright	James Monroe	June 30, 1768	September 23, 1830	62.0	February 16, 1786

	No.	Name	Birthplace	Birthday	Life	Height	Children	Religion	Higher Education	Occupation	Military Service	Term	Party	Vice President	Previous Office	Economy	Foreign Affairs	Military Activity	Other Events	Legacy
0	1	George Washington	Pope's Creek, VA	22-Feb	1732-1799	1.88	0	Episcopalian	None	Plantation Owner, Soldier	Commander-in-Chief of the Continental Army in...	1789-1797	None, Federalist	John Adams	Commander-in-Chief	[' Hamilton established BUS', '1792 Coinage Ac...	['1793 Neutrality in the France-Britain confli...	['1794 Whiskey Rebellion']	['1791 Bill of Rights', '1792 Post Office foun...	He is universally regarded as one of the great...
1	2	John Adams	Braintree, MA	30-Oct	1735-1826	1.70	5	Unitarian	Harvard	Lawyer, Farmer	none	1797-1801	Federalist	Thomas Jefferson	1st Vice President of USA	['1798 Progressive land value tax of up to 1% ...	['1797 the XYZ Affair: a bribe of French agent...	['1798–1800 The Quasi war. Undeclared naval wa...	['1798 Alien & Sedition Act to silence critics...	One of the most experienced men ever to become...
2	3	Thomas Jefferson	Goochland County, VA	13-Apr	1743-1826	1.89	6	unaffiliated Christian	College of William and Mary	Inventor,Lawyer, Architect	Colonel of Virginia militia (without real mili...	1801-1809	Democratic-Republican	Aaron Burr, George Clinton	2nd Vice President of USA	['1807 Embargo Act forbidding foreign trade in...	['1805 Peace Treaty with Tripoli. Piracy stopp...	['1801-05 Naval operation against Tripoli and ...	['1803 The Louisiana purchase', '1804 12th Ame...	Probably the most intelligent man ever to occ...
3	4	James Madison	Port Conway, VA	16-Mar	1751-1836	1.63	0	Episcopalian	Princeton	Plantation Owner, Lawyer	Colonel of Virginia militia (without real mili...	1809-1817	Democratic-Republican	George Clinton, Elbridge Gerry	Secretary of State	[' The first U.S. protective tariff was impose...	['1814 The Treaty of Ghent ends the War of 1812']	['1811 Tippecanoe battle (Harrison vs. Chief T...	['1811 Cumberland Road construction starts (fi...	His leadership in the War of 1812 was particul...
4	5	James Monroe	Monroe Hall, VA	28-Apr	1758-1831	1.83	2	Episcopalian	College of William and Mary	Plantation Owner, Lawyer	Major of the Continental Army	1817-1825	Democratic-Republican	Daniel Tompkins	Secretary of War	['1819 Panic of 1819 (too much land speculatio...	['1823 Monroe Doctrine', '1818 49th parallel s...	['1817 1st Seminole war against Seminole India...	['1819 Florida ceded to US', "1820 Missouri Co...	His presidency contributed to national defense...

	Unnamed: 0	S.No.	start	end	president	prior	party	vice
0	0	1	April 30, 1789	March 4, 1797	George Washington	Commander-in-Chief of the Continental Army ...	Nonpartisan [13]	John Adams
1	1	2	March 4, 1797	March 4, 1801	John Adams	1st Vice President of the United States	Federalist	Thomas Jefferson
2	2	3	March 4, 1801	March 4, 1809	Thomas Jefferson	2nd Vice President of the United States	Democratic- Republican	Aaron Burr
3	3	4	March 4, 1809	March 4, 1817	James Madison	5th United States Secretary of State (1801–...	Democratic- Republican	George Clinton
4	4	5	March 4, 1817	March 4, 1825	James Monroe	7th United States Secretary of State (1811–...	Democratic- Republican	Daniel D. Tompkins

Data Set Name	Provider	URL to Provider	Variable Name in Code
U.S. Presidents' Information	Coursera	Coursera	pres_df_1
First Ladies' Data	Kaggle	Kaggle	pres_df_2
Historical Presidents Physical Data (More)	Kaggle	Kaggle	pres_df_3
U.S. Presidents Dataset (1)	Google Search	Google Search	pres_df_4
U.S. Presidents Popular Vote Percentage Dataset (1)	Kaggle	Kaggle	pres_df_5
Most Common Names of U.S. Presidents (1789-2021) (1)	Statista	Statista	pres_df_6
USA Economic Growth Dataset	World Bank	World Bank	pres_df_7
U.S. GDP During Presidencies Dataset	Statista	Statista	pres_df_8

	order	name	height_cm	height_in	weight_kg	weight_lb	body_mass_index	body_mass_index_range	birth_day	birth_month	...	term_begin_year	term_begin_date	term_end_day	term_end_month	term_end_year	term_end_date	presidency_begin_age	presidency_end_age	political_party	corrected_iq
0	1	George Washington	188	74.0	79.4	175	22.5	Normal	22	2	...	1789	30-04-1789	4.0	3.0	1797.0	04-03-1797	57	65.0	Unaffiliated	140.0
1	2	John Adams	170	67.0	83.9	185	29.0	Overweight	30	10	...	1797	04-03-1797	4.0	3.0	1801.0	04-03-1801	61	65.0	Federalist	155.0
2	3	Thomas Jefferson	189	74.5	82.1	181	23.0	Normal	13	4	...	1801	04-03-1801	4.0	3.0	1809.0	04-03-1809	57	65.0	Democratic-Republican	160.0
3	4	James Madison	163	64.0	55.3	122	20.8	Normal	16	3	...	1809	04-03-1809	4.0	3.0	1817.0	04-03-1817	57	65.0	Democratic-Republican	160.0
4	5	James Monroe	183	72.0	85.7	189	25.6	Overweight	28	4	...	1817	04-03-1817	4.0	3.0	1825.0	04-03-1825	58	66.0	Democratic-Republican	139.0

	year	name	party	term	salary	position_title
0	1789	Washington,George	Unaffiliated	First	25000	PRESIDENT OF THE UNITED STATES
1	1790	Washington,George	Unaffiliated	First	25000	PRESIDENT OF THE UNITED STATES
2	1791	Washington,George	Unaffiliated	First	25000	PRESIDENT OF THE UNITED STATES
3	1792	Washington,George	Unaffiliated	First	25000	PRESIDENT OF THE UNITED STATES
4	1793	Washington,George	Unaffiliated	Second	25000	PRESIDENT OF THE UNITED STATES

	Year	GDP	GDP per capita (in US$ PPP)	GDP (in Bil. US$nominal)	GDP per capita (in US$ nominal)	GDP growth %	Inflation rate %	Unemployment %	Government debt (in % of GDP)	Presidents
0	1981	3207.0	13948.7	3207.0	13948.7	2.50%	10.40%	7.60%	31.00%	Ronald Reagan
1	1982	3343.8	14405.0	3343.8	14405.0	-1.80%	6.20%	9.70%	34.00%	Ronald Reagan
2	1983	3634.0	15513.7	3634.0	15513.7	4.60%	3.20%	9.60%	37.00%	Ronald Reagan
3	1984	4037.7	17086.4	4037.7	17086.4	7.20%	4.40%	7.50%	38.00%	Ronald Reagan
4	1985	4339.0	18199.3	4339.0	18199.3	4.20%	3.50%	7.20%	41.00%	Ronald Reagan

	Unnamed: 0	Year	CPI	GDPdeflator	population.K	realGDPperCapita	executive	war	battleDeaths	battleDeathsPMP	...	unemployment	unempSource	fedReceipts	fedOutlays	fedSurplus	fedDebt	fedReceipts_pGDP	fedOutlays_pGDP	fedSurplus_pGDP	fedDebt_pGDP
0	1610	1610	NaN	NaN	0.350	NaN	JamesI	NaN	NaN	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
1	1620	1620	NaN	NaN	2.302	NaN	JamesI	NaN	NaN	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
2	1630	1630	NaN	NaN	4.646	NaN	CharlesI	NaN	NaN	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
3	1640	1640	NaN	NaN	26.634	NaN	CharlesI	NaN	NaN	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
4	1650	1650	NaN	NaN	50.368	NaN	Cromwell	NaN	NaN	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN

	President	Born	Post-presidency timespan	Died	Age	Start Date of presidency	Start Age of presidency	End of Presidency Age	End of Presidency Date
0	George Washington	1732-02-22	1015 days 00:00:00	1799-12-14	24750 days	1789-04-30	20872 days	23735 days	1797-03-04
1	John Adams	1735-10-30	9247 days 00:00:00	1826-07-04	33097 days	1797-03-04	22390 days	23850 days	1801-03-04
2	Thomas Jefferson	1743-04-13	6327 days 00:00:00	1826-07-04	30377 days	1801-03-04	21130 days	24050 days	1809-03-04
3	James Madison	1751-03-16	7051 days 00:00:00	1836-06-28	31129 days	1809-03-04	21158 days	24078 days	1817-03-04
4	James Monroe	1758-04-28	2312 days 00:00:00	1831-07-04	26712 days	1817-03-04	21480 days	24400 days	1825-03-04
5	John Quincy Adams	1767-07-11	6926 days 00:00:00	1848-02-23	29427 days	1825-03-04	21041 days	22501 days	1829-03-04
6	Andrew Jackson	1767-03-15	3016 days 00:00:00	1845-06-08	28555 days	1829-03-04	22619 days	25539 days	1837-03-04
7	Martin Van Buren	1782-12-05	7807 days 00:00:00	1862-07-24	29066 days	1837-03-04	19799 days	21259 days	1841-03-04
8	William H. Harrison	1773-02-09	Died in Office	1841-04-04	24874 days	1841-03-04	24843 days	24874 days	1841-04-04
9	John Tyler	1790-03-29	6160 days 00:00:00	1862-01-18	26210 days	1841-04-04	18621 days	20050 days	1845-03-04
10	James K. Polk	1795-11-02	103 days 00:00:00	1849-06-15	19570 days	1845-03-04	18007 days	19467 days	1849-03-04
11	Zachary Taylor	1784-11-24	Died in Office	1850-07-09	23952 days	1849-03-04	23460 days	23952 days	1850-07-09
12	Millard Fillmore	1800-01-07	7669 days 00:00:00	1874-03-08	27070 days	1850-07-09	18433 days	19401 days	1853-03-04
13	Franklin Pierce	1804-11-23	4598 days 00:00:00	1869-10-08	23679 days	1853-03-04	17621 days	19081 days	1857-03-04
14	James Buchanan	1791-04-23	2644 days 00:00:00	1868-06-01	28144 days	1857-03-04	24040 days	25500 days	1861-03-04
15	Abraham Lincoln	1809-02-12	Died in Office	1865-04-15	20502 days	1861-03-04	19000 days	20502 days	1865-04-15
16	Andrew Johnson	1808-12-29	2339 days 00:00:00	1875-07-31	24304 days	1865-04-15	20547 days	21965 days	1869-03-04
17	Ulysses S. Grant	1822-04-27	3061 days 00:00:00	1885-07-23	23082 days	1869-03-04	17101 days	20021 days	1877-03-04
18	Rutherford B. Hayes	1822-10-04	4334 days 00:00:00	1893-01-17	25655 days	1877-03-04	19861 days	21321 days	1881-03-04
19	James A. Garfield	1831-11-19	Died in Office	1881-09-19	18189 days	1881-03-04	17990 days	18189 days	1881-09-19
20	Chester A. Arthur	1829-10-05	624 days 00:00:00	1886-11-18	20849 days	1881-09-19	18964 days	20225 days	1885-03-04
21	Grover Cleveland	1837-03-18	1460 days 00:00:00	1908-06-24	26013 days	1885-03-04	17506 days	18966 days	1889-03-04
22	Benjamin Harrison	1833-08-20	2929 days 00:00:00	1901-03-13	24660 days	1889-03-04	20271 days	21731 days	1893-03-04
23	Grover Cleveland	1837-03-18	4127 days 00:00:00	1908-06-24	26013 days	1893-03-04	20426 days	21886 days	1897-03-04
24	William McKinley	1843-01-29	Died in Office	1901-09-14	21398 days	1897-03-04	19744 days	21398 days	1901-09-14
25	Theodore Roosevelt	1858-10-27	3593 days 00:00:00	1919-01-06	21971 days	1901-09-14	15652 days	18378 days	1909-03-04
26	William H. Taft	1857-09-15	6209 days 00:00:00	1930-03-08	26454 days	1909-03-04	18785 days	20245 days	1913-03-04
27	Woodrow Wilson	1856-12-28	1066 days 00:00:00	1924-02-03	24492 days	1913-03-04	20506 days	23426 days	1921-03-04
28	Warren G. Harding	1865-11-02	Died in Office	1923-08-02	21078 days	1921-03-04	20197 days	21078 days	1923-08-02
29	Calvin Coolidge	1872-07-04	1402 days 00:00:00	1933-01-05	22085 days	1923-08-02	18644 days	20683 days	1929-03-04
30	Herbert Hoover	1874-08-10	11545 days 00:00:00	1964-10-20	32921 days	1929-03-04	19916 days	21376 days	1933-03-04
31	Franklin D. Roosevelt	1882-01-30	Died in Office	1945-04-12	23067 days	1933-03-04	18648 days	23067 days	1945-04-12
32	Harry S. Truman	1884-05-08	7276 days 00:00:00	1972-12-26	32352 days	1945-04-12	22239 days	25077 days	1953-01-20
33	Dwight D. Eisenhower	1890-10-14	2987 days 00:00:00	1969-03-28	28635 days	1953-01-20	22728 days	25648 days	1961-01-20
34	John F. Kennedy	1917-05-29	Died in Office	1963-11-22	16967 days	1961-01-20	15931 days	16967 days	1963-11-22
35	Lyndon B. Johnson	1908-08-27	1462 days 00:00:00	1973-01-22	23508 days	1963-11-22	20162 days	22046 days	1969-01-20
36	Richard Nixon	1913-01-09	7191 days 00:00:00	1994-04-22	29668 days	1969-01-20	20451 days	22477 days	1974-08-09
37	Gerald Ford	1913-07-14	10925 days 00:00:00	2006-12-26	34110 days	1974-08-09	22291 days	23185 days	1977-01-20
38	Jimmy Carter	1924-10-01	14045 days 00:00:00	NaT	34596 days	1977-01-20	19091 days	20551 days	1981-01-20
39	Ronald Reagan	1911-02-06	5612 days 00:00:00	2004-06-05	34065 days	1981-01-20	25534 days	28454 days	1989-01-20
40	George H. W. Bush	1924-06-12	9439 days 00:00:00	2018-11-30	34481 days	1989-01-20	23582 days	25042 days	1993-01-20
41	Bill Clinton	1946-08-19	6745 days 00:00:00	NaT	26609 days	1993-01-20	16944 days	19864 days	2001-01-20
42	George W. Bush	1946-07-06	3825 days 00:00:00	NaT	26653 days	2001-01-20	19908 days	22828 days	2009-01-20
43	Barack Obama	1961-08-04	905 days 00:00:00	NaT	21149 days	2009-01-20	17324 days	20244 days	2017-01-20
44	Donald J. Trump	1946-06-14	NaT	NaT	25770 days	2017-01-20	25770 days	27232 days	2021-01-20
45	Joe Biden	1942-11-20	NaT	NaT	28531 days	2021-01-20	28167 days	29627 days	2024-11-05

	year	party	term	salary	position_title	President
227	2016	Democratic	Second	400000	PRESIDENT OF THE UNITED STATES	Barack H. Obama
424	2016	Democratic	Second	230700	VICE PRESIDENT OF THE UNITED STATES	Joseph R. Biden

	Relation to President	First Lady Name	President	Date of Born, First Lady	Date of Death, First Lady	Age at Death, First Lady	Date of Marriage
0	Husband	Martha Dandridge	George Washington	1731-06-13	1802-05-22	70.0	1759-01-06
1	Husband	Abigail Smith	John Adams	1744-11-22	1818-10-28	73.0	1764-10-25
2	Father	Martha Jefferson	Thomas Jefferson	1772-09-27	1836-10-10	64.0	NaT
3	Husband	Dolley Payne	James Madison	1768-05-20	1849-07-12	81.0	1794-09-14
4	Husband	Elizabeth Kortright	James Monroe	1768-06-30	1830-09-23	62.0	1786-02-16
5	Husband	Louisa Catherine Johnson	John Quincy Adams	1775-02-12	1852-05-15	77.0	1797-07-26
6	Uncle	Emily Donelson	Andrew Jackson	1807-06-01	1836-12-19	29.0	NaT
7	Father-in-law	Sarah Yorke	Andrew Jackson	1803-07-16	1887-08-23	84.0	NaT
8	Father-in-law	Sarah Angelica Singleton	Martin Van Buren	1818-02-13	1877-12-29	59.0	NaT
9	Husband	Anna Tuthill Symmes	William Henry Harrison	1775-07-25	1864-02-25	88.0	1795-11-22
10	Father-in-law	Jane Irwin	William Henry Harrison	1804-07-23	1846-05-11	41.0	NaT
11	Husband	Letitia Christian	John Tyler	1790-11-12	1842-09-10	51.0	1813-03-29
12	Father-in-law	Elizabeth Priscilla Cooper	John Tyler	1816-06-14	1889-12-29	73.0	NaT
13	Husband	Julia Gardiner	John Tyler	1820-05-04	1889-07-10	69.0	1844-06-26
14	Husband	Sarah Childress	James K. Polk	1803-09-04	1891-08-14	87.0	1824-01-01
15	Husband	Margaret Mackall Smith	Zachary Taylor	1788-09-21	1852-08-14	63.0	1810-06-21
16	Husband	Abigail Powers	Millard Fillmore	1798-03-13	1853-03-30	55.0	1826-02-05
17	Husband	Jane Means Appleton	Franklin Pierce	1806-03-12	1863-12-02	57.0	1834-11-19
18	Uncle	Harriet Rebecca Lane	James Buchanan	1830-05-09	1903-07-03	73.0	NaT
19	Husband	Mary Ann Todd	Abraham Lincoln	1818-12-13	1882-07-16	63.0	1842-11-04
20	Husband	Eliza McCardle	Andrew Johnson	1810-10-04	1876-01-15	65.0	1827-05-17
21	Husband	Julia Boggs Dent	Ulysses S. Grant	1826-01-26	1902-12-14	76.0	1848-08-22
22	Husband	Lucy Ware Webb	Rutherford B. Hayes	1831-08-28	1889-06-25	57.0	1852-12-30
23	Husband	Lucretia Rudolph	James A. Garfield	1832-04-19	1918-03-14	85.0	1858-11-11
24	Brother	Mary Arthur McElroy	Chester A. Arthur	1841-07-05	1917-01-08	75.0	NaT
25	Brother	Rose Elizabeth Cleveland	Grover Cleveland	1846-06-13	1918-11-22	72.0	NaT
26	Husband	Frances Clara Folsom	Grover Cleveland	1864-07-21	1947-10-29	83.0	1886-06-02
27	Husband	Caroline Lavinia Scott	Benjamin Harrison	1832-10-01	1892-10-25	60.0	1853-10-20
28	Father	Mary Scott Harrison	Benjamin Harrison	1858-04-03	1930-10-28	72.0	NaT
29	Husband	Frances Clara Folsom	Grover Cleveland	1864-07-21	1947-10-29	83.0	1886-06-02
30	Husband	Ida Saxton	William McKinley	1847-06-08	1907-05-26	59.0	1871-01-25
31	Husband	Edith Kermit Carow	Theodore Roosevelt	1861-08-06	1948-09-30	87.0	1886-12-02
32	Husband	Helen Louise Herron	William H. Taft	1861-06-02	1943-05-22	81.0	1886-06-19
33	Husband	Ellen Louise Axson	Woodrow Wilson	1860-05-15	1914-08-06	54.0	1885-06-24
34	Father	Margaret Woodrow Wilson	Woodrow Wilson	1886-04-16	1944-02-12	57.0	NaT
35	Husband	Edith Bolling	Woodrow Wilson	1872-10-15	1961-12-28	89.0	1915-12-18
36	Husband	Florence Mabel Kling	Warren G. Harding	1860-08-15	1924-11-21	64.0	1891-07-08
37	Husband	Grace Anna Goodhue	Calvin Coolidge	1879-01-03	1957-07-08	78.0	1905-10-04
38	Husband	Lou Henry	Herbert Hoover	1874-03-29	1944-01-07	69.0	1899-02-10
39	Husband	Anna Eleanor Roosevelt	Franklin D. Roosevelt	1884-10-11	1962-11-07	78.0	1905-03-17

Exploring U.S. Presidents: A Multidimensional Study

Introduction¶

Research Objectives¶

Methodology¶

1. Data Collection¶

2. Data Cleaning and Integration¶

3. Exploratory Data Analysis (EDA)¶

4. In-Depth Data Analysis¶

5. Data Visualization¶

6. Interpretation and Conclusion¶

Acknowledgements¶

1. Data Collection

Import the important libraries

Sourcing the Datasets: My Exploration and Methods

1. Coursera:¶

2. Kaggle:¶

3. Google Search:¶

4. Statista:¶

5. World Bank:¶

Data Sets Information

Interactive Resource Viewer in JupyterLab¶

How it works:¶

Instructions:¶

load the dataset & start discovering

2. Data Cleaning and Integration

1.1 U.S. Presidents' Information : pres_df_1

Data Cleaning Steps:¶

Achievements:¶

1.2 First Ladies' Data : pres_df_2

1.3 Historical Presidents Physical Data (More) : pres_df_3

1.4 U.S. Presidents Dataset (1) : pres_df_4

1.5 U.S. Presidents Popular Vote Percentage Dataset (1) : pres_df_5

1.6 Most Common Names of U.S. Presidents (1789-2021) (1) : pres_df_6

1.7 USA Economic Growth Dataset : pres_df_7

1.8 U.S. GDP During Presidencies Dataset : pres_df_8

2. Data Integration

Achievements:¶

3→ 5 Exploratory Data Analysis, Data Visualization & In-Depth Data Analysis

Presidents and Their Birthplaces by Political Party

Visual Elements:¶

Insights:¶

Interactive Functionality:¶

Birthplaces of U.S. Presidents by Political Party

Post-presidency Timespan of U.S. Presidents

Age of U.S. Presidents by Political Party

Age of U.S. Presidents at the Start of Presidency

Pie Chart: Number of Children of U.S. Presidents

Bar Chart: Number of Children of U.S. Presidents

Bar Chart - U.S. Presidents by Religion and Political Party

Pie Chart - Number of U.S. Presidents by Religion

Higher Education of U.S. Presidents

1. Word Cloud¶

2. Venn Diagram¶

3. Interactive Tool¶

Exploring Occupations of U.S. Presidents: A Visual Analysis

1. Word Cloud: What Were the Most Frequent Occupations of U.S. Presidents?¶

2. Bar Chart: How Do Occupations Vary Among U.S. Presidents?¶

3. Interactive Tool: What Was the Occupation of a Specific U.S. President?¶

4. Interactive Tool to Identify Most Frequent Occupations by Party: Which Occupations Prevail Within Each Political Party?¶

Exploring U.S. Presidents' Military Service - TreeMap Visualization

What is a TreeMap?¶

Which Previous Offices Did U.S. Presidents Hold Before Their Presidency

Word Cloud - Most Frequent Previous Offices of U.S. Presidents¶

Sunburst Chart - U.S. Presidents and Their Parties¶

Interactive Economy Data Display Tool

How to Use the Tool¶

Exploring U.S. Presidents: Their Foreign Affairs

Word Cloud for Foreign Affairs¶

Word Scatter Plot for Foreign Affairs¶

Interactive Tool for Exploring Foreign Affairs¶

Explore U.S. Presidents' Historical Data

What are the Most Frequent U.S. President Names and Their Party Distribution?

What is the distribution of the age at marriage for the First Ladies of the United States, and who were the Presidents they married?

Height vs. Weight with Body Mass Index and Political Party

Which States Produced the Most U.S. Presidents?

How Many U.S. Presidents Were Born in Each State? - Political Affiliation Bar Chart¶

Which States Produced the Most U.S. Presidents? - Interactive Birthplace Map¶

Analyzing U.S. Presidents' Intelligence and Cognitive Abilities

1. Horizontal Bar Charts:¶

2. Box Plot:¶