pip install pandas matplotlib seaborn scikit-learn ydata-profiling

import pandas as pd
from ydata_profiling import ProfileReport
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_squared_error, r2_score

# Read the data into a DataFrame
db_path = "data/"
df = pd.read_csv(db_path + "ecommerce_customers.csv")

# Display first few rows
df.head()

df.describe()

# Select feature columns
X = df[['Avg. Session Length', 'Time on App', 
        'Time on Website', 'Length of Membership']]

# Select target variable
y = df['Yearly Amount Spent']

X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.3, random_state=1
)

# Initialize the model
model = LinearRegression()

# Train the model
model.fit(X_train, y_train)

# Make predictions
y_pred = model.predict(X_test)

# Calculate Mean Squared Error
mse = mean_squared_error(y_test, y_pred)
print(f"Mean Squared Error: {mse:.2f}")

# Calculate R-squared
r2 = r2_score(y_test, y_pred)
print(f"R² Score: {r2:.4f}")

Mean Squared Error: 80.90
R² Score: 0.9885

# Get model coefficients
coefficients = pd.DataFrame({
    'Feature': X.columns,
    'Coefficient': model.coef_
})
print(coefficients)

# Get intercept
print(f"\nIntercept: {model.intercept_:.2f}")

import matplotlib.pyplot as plt
import seaborn as sns

# Create scatter plot
plt.figure(figsize=(10, 6))
plt.scatter(y_test, y_pred, alpha=0.6)
plt.plot([y_test.min(), y_test.max()], 
         [y_test.min(), y_test.max()], 
         'r--', lw=2)
plt.xlabel('Actual Yearly Amount Spent')
plt.ylabel('Predicted Yearly Amount Spent')
plt.title('Actual vs Predicted Customer Spending')
plt.tight_layout()
plt.show()

ModuleNotFoundError: No module named 'sklearn'

pip install scikit-learn

FileNotFoundError: [Errno 2] No such file or directory: 'data/ecommerce_customers.csv'

jupyter: command not found

pip install jupyter notebook