#DATE PRE PROCESSING CODE.py

#DATE PRE PROCESSING CODE =

import pandas as pd
import dask.dataframe as dd
import numpy as np
import matplotlib.pyplot as plt

#This loads datasets
df = dd.read_csv("Trips_By_Distance.csv")
df_full = dd.read_csv("Trips_Full_Data.csv")

#This handles missing Values
df = df.fillna(df.mean())
df_full = df_full.fillna(df_full.mean())

#Data Cleaning
df["Population Staying at Home"] = df["Population Staying at Home"].astype("int64")
df_full["Week"] = df_full["Week"].astype("int64")

#Grouping Data
weekly_stay_home = df.groupby(by='Week')['Population Staying at Home'].mean().compute()
weekly_trips = df_full.groupby(by='Week')['Trips 1-25 Miles'].mean().compute()

#Data Visualization
plt.figure(figsize=(10, 7))
plt.bar(weekly_stay_home.index, weekly_stay_home.values, color='orange', width=0.4)
plt.xlabel("Week")
plt.ylabel("Average Population Staying at Home")
plt.title("Average Population Staying at Home per Week")
plt.grid()
plt.show()

plt.figure(figsize=(10, 7))
plt.bar(weekly_trips.index, weekly_trips.values, color='blue', width=0.4)
plt.xlabel("Week")
plt.ylabel("Average Trips 1-25 Miles")
plt.title("Average Trips 1-25 Miles per Week")
plt.grid()
plt.show()