Time-Series & Datetime EDA

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns

np.random.seed(42)

# Create a time series dataset (e-commerce transactions)
dates = pd.date_range("2023-01-01", "2023-12-31", freq="h")  # hourly 2023
n = len(dates)

df = pd.DataFrame({
    "timestamp":  dates,
    "sales":      (200 + 50 * np.sin(np.arange(n) * 2 * np.pi / 24)  # daily cycle
                   + 100 * np.sin(np.arange(n) * 2 * np.pi / (24*7))  # weekly cycle
                   + np.random.normal(0, 20, n)).clip(0),              # noise
    "is_fraud":   np.random.choice([0, 1], n, p=[0.99, 0.01]),
})

# STEP 1: EXTRACT DATETIME FEATURES
df["hour"]         = df["timestamp"].dt.hour
df["day_of_week"]  = df["timestamp"].dt.dayofweek      # 0=Mon, 6=Sun
df["day_name"]     = df["timestamp"].dt.day_name()
df["month"]        = df["timestamp"].dt.month
df["month_name"]   = df["timestamp"].dt.month_name()
df["quarter"]      = df["timestamp"].dt.quarter
df["is_weekend"]   = df["timestamp"].dt.dayofweek.isin([5, 6]).astype(int)
df["week_of_year"] = df["timestamp"].dt.isocalendar().week.astype(int)

print("Extracted datetime features:")
print(df[["timestamp", "hour", "day_of_week", "month", "is_weekend"]].head(5))

# STEP 2: VISUALIZE TEMPORAL PATTERNS
fig, axes = plt.subplots(2, 2, figsize=(14, 10))

# Daily pattern
hourly_avg = df.groupby("hour")["sales"].mean()
axes[0, 0].plot(hourly_avg.index, hourly_avg.values, color="steelblue", linewidth=2)
axes[0, 0].fill_between(hourly_avg.index, hourly_avg.values, alpha=0.3, color="steelblue")
axes[0, 0].set_title("Average Sales by Hour of Day")
axes[0, 0].set_xlabel("Hour")

# Weekly pattern
day_order = ["Monday","Tuesday","Wednesday","Thursday","Friday","Saturday","Sunday"]
weekly_avg = df.groupby("day_name")["sales"].mean().reindex(day_order)
colors_week = ["steelblue"] * 5 + ["tomato"] * 2  # weekend in red
weekly_avg.plot(kind="bar", ax=axes[0, 1], color=colors_week, rot=30)
axes[0, 1].set_title("Average Sales by Day of Week")

# Monthly pattern
monthly_avg = df.groupby("month")["sales"].mean()
axes[1, 0].plot(monthly_avg.index, monthly_avg.values, marker="o", color="coral", linewidth=2)
axes[1, 0].set_title("Average Sales by Month")
axes[1, 0].set_xticks(range(1, 13))

# Fraud by hour
fraud_by_hour = df.groupby("hour")["is_fraud"].mean()
axes[1, 1].bar(fraud_by_hour.index, fraud_by_hour.values, color="tomato", alpha=0.7)
axes[1, 1].set_title("Fraud Rate by Hour of Day")
axes[1, 1].set_xlabel("Hour")

plt.tight_layout()
plt.savefig("temporal_eda.png", dpi=100, bbox_inches="tight")
plt.show()

# STEP 3: CYCLICAL ENCODING (for ML models that don't know 23 is close to 0)
df["hour_sin"] = np.sin(2 * np.pi * df["hour"] / 24)
df["hour_cos"] = np.cos(2 * np.pi * df["hour"] / 24)
df["day_sin"]  = np.sin(2 * np.pi * df["day_of_week"] / 7)
df["day_cos"]  = np.cos(2 * np.pi * df["day_of_week"] / 7)
print("\nCyclical encoding: hour=23 and hour=0 are now close in encoded space")
print(f"  Hour 23: sin={df['hour_sin'].iloc[23]:.3f}, cos={df['hour_cos'].iloc[23]:.3f}")
print(f"  Hour  0: sin={df['hour_sin'].iloc[0]:.3f}, cos={df['hour_cos'].iloc[0]:.3f}")