# -*- coding: utf-8 -*-
"""1957_249_949

Automatically generated by Colab.

Original file is located at
    https://colab.research.google.com/drive/1q6DU2jTXfNY0uMxaBV2w2niCrYcsW86S
"""

import numpy as np
import pandas as pd

import os
for dirname, _, filenames in os.walk('/kaggle/input'):
  for filename in filenames:
    print(os.path.join(dirname, filename))

import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestRegressor
from sklearn.metrics import mean_squared_error, mean_absolute_error, r2_score
import matplotlib.pyplot as plt
import seaborn as sns

data = pd.read_csv('/content/internet_usage.csv')

data.head()

data.tail()

data.describe()

numeric_cols = data.columns[2:]
data[numeric_cols] = data[numeric_cols].apply(pd.to_numeric, errors='coerce')
data = data.dropna(subset=numeric_cols, how='all')
data = data.fillna(data.mean(numeric_only=True))

years = [int(col) for col in numeric_cols]
data['avg_usage'] = data[numeric_cols].mean(axis=1)
data['usage_change'] = data[numeric_cols].iloc[:, -1] - data[numeric_cols].iloc[:, 0]
data['rate_change'] = data['usage_change'] / (years[-1] - years [0])

features = ['avg_usage', 'usage_change', 'rate_change']
 target_year = 2023
 target = str(target_year)

 X = data[features]
 y= data[target]

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

model = RandomForestRegressor(n_estimators=100, random_state=42)
model.fit(X_train, y_train)

y_pred = model.predict(X_test)

mse = mean_squared_error(y_test, y_pred)
mae = mean_absolute_error(y_test, y_pred)
r2 = r2_score(y_test, y_pred)

print(f"Mean Squared Error: {mse}")
print(f"Mean Absolute Error: {mae}")
print(f"R-squared: {r2}")

plt.figure(figsize=(10, 6))
plt.scatter(y_test, y_pred)
plt.xlabel("Actual Values")
plt.ylabel("Predicted Values")
plt.title("Actual vs. Predicted Values")
plt.plot([min(y_test), max(y_test)], [min(y_test), max(y_test)], color='red')
plt.show()

feature_importance = model.feature_importances_
feature_names = X.columns

plt.figure(figsize=(10, 6))
sns.barplot(x=feature_importance, y=feature_names)
plt.title("Feature Importance")
plt.show()

def predict_future_usage(model, data, features, future_years):
  predictions = {}
  for year in future_years:
    new_data = data.copy()
    new_data[str(year)] = model.predict(new_data[features])
    predictions[year] = new_data[str(year)]
    data[str(year)] = new_data[str(year)]

    return predictions

future_years = [2024, 2025]
future_predictions = predict_future_usage(model, data, features, future_years)

print("\nFuture Predictions:")
for year, predictions in future_predictions.items():
  print(f"Predictions for {year}:")
  print(predictions.head())