import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns

# Load data and set index to 'date'
df = pd.read_csv("fcc-forum-pageviews.csv", index_col="date", parse_dates=True)

# Clean data: Remove top 2.5% and bottom 2.5% of page views
df = df[(df["value"] >= df["value"].quantile(0.025)) & (df["value"] <= df["value"].quantile(0.975))]

def draw_line_plot():
    fig, ax = plt.subplots(figsize=(12, 6))
    ax.plot(df.index, df['value'], color='red', linewidth=1)
    ax.set_title("Daily freeCodeCamp Forum Page Views 5/2016-12/2019")
    ax.set_xlabel("Date")
    ax.set_ylabel("Page Views")
    
    fig.savefig('line_plot.png')
    return fig

def draw_bar_plot():
    df_bar = df.copy()
    df_bar['year'] = df_bar.index.year
    df_bar['month'] = df_bar.index.month
    df_bar_grouped = df_bar.groupby(['year', 'month'])['value'].mean().unstack()

    fig = df_bar_grouped.plot(kind='bar', figsize=(10, 6)).figure
    plt.xlabel("Years")
    plt.ylabel("Average Page Views")
    plt.legend(title="Months", labels=["Jan", "Feb", "Mar", "Apr", "May", "Jun", "Jul", "Aug", "Sep", "Oct", "Nov", "Dec"])
    
    fig.savefig('bar_plot.png')
    return fig

def draw_box_plot():
    df_box = df.copy()
    df_box.reset_index(inplace=True)
    df_box['year'] = df_box['date'].dt.year
    df_box['month'] = df_box['date'].dt.strftime('%b')
    df_box['month_num'] = df_box['date'].dt.month
    df_box = df_box.sort_values('month_num')

    fig, axes = plt.subplots(1, 2, figsize=(15, 6))

    sns.boxplot(x='year', y='value', data=df_box, ax=axes[0])
    axes[0].set_title('Year-wise Box Plot (Trend)')
    axes[0].set_xlabel('Year')
    axes[0].set_ylabel('Page Views')

    sns.boxplot(x='month', y='value', data=df_box, ax=axes[1])
    axes[1].set_title('Month-wise Box Plot (Seasonality)')
    axes[1].set_xlabel('Month')
    axes[1].set_ylabel('Page Views')

    fig.savefig('box_plot.png')
    return fig

if __name__ == "__main__":
    draw_line_plot()
    draw_bar_plot()
    draw_box_plot()

import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
import numpy as np

df = pd.read_csv("medical_examination.csv")

df['BMI'] = df['weight'] / ((df['height'] / 100) ** 2)
df['overweight'] = (df['BMI'] > 25).astype(int)
df.drop(columns=['BMI'], inplace=True)

df['cholesterol'] = df['cholesterol'].apply(lambda x: 0 if x == 1 else 1)
df['gluc'] = df['gluc'].apply(lambda x: 0 if x == 1 else 1)

def draw_cat_plot():
    df_cat = pd.melt(df, id_vars=['cardio'], value_vars=['cholesterol', 'gluc', 'smoke', 'alco', 'active', 'overweight'])
    df_cat = df_cat.groupby(['cardio', 'variable', 'value']).size().reset_index(name='total')
    fig = sns.catplot(x='variable', y='total', hue='value', col='cardio', data=df_cat, kind='bar')
    return fig

def draw_heat_map():
    df_heat = df[
        (df['ap_lo'] <= df['ap_hi']) &
        (df['height'] >= df['height'].quantile(0.025)) &
        (df['height'] <= df['height'].quantile(0.975)) &
        (df['weight'] >= df['weight'].quantile(0.025)) &
        (df['weight'] <= df['weight'].quantile(0.975))
    ]
    
    corr = df_heat.corr()
    mask = np.triu(np.ones_like(corr, dtype=bool))
    fig, ax = plt.subplots(figsize=(12, 10))
    sns.heatmap(corr, mask=mask, annot=True, fmt='.1f', ax=ax, cmap='coolwarm', vmax=.3, center=0, square=True, linewidths=.5, cbar_kws={"shrink": .5})
    return fig

if __name__ == "__main__":
    draw_cat_plot()
    draw_heat_map()

import pandas as pd

def demographic_data_analyzer():
    df = pd.read_csv('adult.data', header=None, names=[
        'age', 'workclass', 'fnlwgt', 'education', 'education-num', 'marital-status', 
        'occupation', 'relationship', 'race', 'sex', 'capital-gain', 'capital-loss', 
        'hours-per-week', 'native-country', 'salary'
    ])

    race_count = df['race'].value_counts()

    average_age_men = round(df[df['sex'] == 'Male']['age'].mean(), 1)

    percentage_bachelors = round((df[df['education'] == 'Bachelors'].shape[0] / df.shape[0]) * 100, 1)

    advanced_education = df['education'].isin(['Bachelors', 'Masters', 'Doctorate'])
    percentage_advanced_education_rich = round(
        (df[advanced_education & (df['salary'] == '>50K')].shape[0] / df[advanced_education].shape[0]) * 100, 1)

    not_advanced_education = ~advanced_education
    percentage_not_advanced_education_rich = round(
        (df[not_advanced_education & (df['salary'] == '>50K')].shape[0] / df[not_advanced_education].shape[0]) * 100, 1)

    min_work_hours = df['hours-per-week'].min()

    min_workers = df[df['hours-per-week'] == min_work_hours]
    rich_percentage = round((min_workers[min_workers['salary'] == '>50K'].shape[0] / min_workers.shape[0]) * 100, 1)

    countries = df[df['salary'] == '>50K']['native-country'].value_counts()
    total_by_country = df['native-country'].value_counts()
    highest_earning_country_percentage = round((countries / total_by_country * 100).max(), 1)
    highest_earning_country = (countries / total_by_country * 100).idxmax()

    india_high_earners = df[(df['native-country'] == 'India') & (df['salary'] == '>50K')]
    top_IN_occupation = india_high_earners['occupation'].value_counts().idxmax()

    return {
        'race_count': race_count,
        'average_age_men': average_age_men,
        'percentage_bachelors': percentage_bachelors,
        'percentage_advanced_education_rich': percentage_advanced_education_rich,
        'percentage_not_advanced_education_rich': percentage_not_advanced_education_rich,
        'min_work_hours': min_work_hours,
        'rich_percentage': rich_percentage,
        'highest_earning_country': highest_earning_country,
        'highest_earning_country_percentage': highest_earning_country_percentage,
        'top_IN_occupation': top_IN_occupation
    }

if __name__ == "__main__":
    results = demographic_data_analyzer()
    for key, value in results.items():
        print(f"{key}: {value}")