FunctionLibrary.py

import pandas as pd
import os
import sys
import warnings
import plotly.express as px

warnings.filterwarnings("ignore")

def check_file(file_path):
    if not os.path.isfile(file_path):
        print(f'Error: File "{file_path}" not found. Please check if you are in the correct directory.')
        sys.exit(1)
    return file_path

def clean_loandata(df):
    for col in df.select_dtypes(include = 'object'):
        if col in df.columns:
            df[col].fillna(df[col].mode()[0], inplace = True)
            df[col] = df[col].astype('category')
            df[col] = df[col].str.strip().str.lower()
            
    for col in df.select_dtypes(include = ['int64', 'float64']):
        if col in df.columns:
            df[col].fillna(df[col].median(), inplace= True)
            upper = df[col].quantile(0.99)
            
            df[col] = df[col].apply(lambda x: upper if x >upper else x).round(2)
      
    return df

def pie_chart(df, column_name):
    pie_chart_count = df[column_name].value_counts()
    pie_chart_status = px.pie(pie_chart_count, names = pie_chart_count.index, 
    title = column_name)
    pie_chart_status.show()

def bar_graph(df, column_name):
    bar_graph_count = df[column_name].value_counts()
    fig_bar_graph = px.bar(bar_graph_count, 
    x=bar_graph_count.index, 
    y=bar_graph_count.values, 
    title= column_name+' Distribution')
    fig_bar_graph.show()    

def histogram(df, column_name):
    fig_histogram = px.histogram(df, x = column_name, 
    title = column_name+' Distribution')
    fig_histogram.show()

def box_plot(df, x_column, y_column):
    fig_box_plot = px.box(df, x = x_column,y = y_column, color = x_column,
    title = x_column + ' vs ' + y_column)
    fig_box_plot.show()

    Q1 = df[y_column].quantile(0.25)
    Q3 = df[y_column].quantile(0.75)
    IQR = Q3 -Q1

    lower_bound = Q1 -1.5 *IQR
    upper_bound = Q3 +1.5 *IQR

    df = df[(df[y_column] >= lower_bound) & (df[y_column] <= upper_bound)]
    
def double_histogram(df, one_name, two_name):
    fig_double_histogram = px.histogram(df, x = one_name, color = two_name, barmode = 'group',
    title = two_name+' vs '+one_name)
    fig_double_histogram.show()