AI Assistance

import pandas as pd

# Load sales data
df = pd.read_csv('data/sales.csv')
print(f"Loaded {len(df)} rows")
df.head()

import matplotlib.pyplot as plt
import numpy as np
from scipy import stats

# Create line plot with trend
plt.figure(figsize=(12, 6))
plt.plot(df['date'], df['revenue'], label='Revenue', marker='o')

# Add trend line
x = np.arange(len(df))
slope, intercept, r_value, p_value, std_err = stats.linregress(x, df['revenue'])
plt.plot(df['date'], slope * x + intercept, 'r--', label=f'Trend (R²={r_value**2:.3f})')

plt.xlabel('Date')
plt.ylabel('Revenue ($)')
plt.title('Revenue Over Time')
plt.legend()
plt.xticks(rotation=45)
plt.tight_layout()
plt.show()

# Remove duplicate rows
df_clean = df.drop_duplicates()
print(f"Removed {len(df) - len(df_clean)} duplicate rows")

# Fill missing values with median for numeric columns
numeric_cols = df_clean.select_dtypes(include=[np.number]).columns
for col in numeric_cols:
    if df_clean[col].isnull().any():
        median_val = df_clean[col].median()
        df_clean[col].fillna(median_val, inplace=True)
        print(f"Filled {col} missing values with median: {median_val}")

df_clean.info()

from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import train_test_split
from sklearn.metrics import classification_report, confusion_matrix

# Prepare features and target
X = df[['age', 'tenure', 'monthly_charges', 'total_charges']]
y = df['churn']

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

# Train model
rf = RandomForestClassifier(n_estimators=100, random_state=42)
rf.fit(X_train, y_train)

# Evaluate
y_pred = rf.predict(X_test)
print("Classification Report:")
print(classification_report(y_test, y_pred))
print("\nConfusion Matrix:")
print(confusion_matrix(y_test, y_pred))