# ── Variables ────────────────────────────────────────────
name  = "Alice"
age   = 28
score = 94.5

# ── List & Dictionary ────────────────────────────────────
features = ["age", "income", "score"]
record   = {"name": "Alice", "age": 28, "churn": False}

# ── Loop over features ───────────────────────────────────
for feat in features:
    print(f"Feature: {feat}")

# ── Condition (filtering logic) ──────────────────────────
if score >= 90:
    print("High performer")
else:
    print("Needs improvement")

# ── Function (reusable logic block) ──────────────────────
def normalize(value, min_v, max_v):
    return (value - min_v) / (max_v - min_v)

import pandas as pd

# ── Load dataset ─────────────────────────────────────────
df = pd.read_csv("sales_data.csv")

# ── First look ───────────────────────────────────────────
print(df.head())         # first 5 rows
print(df.shape)          # (rows, columns)

# ── Understand the data ──────────────────────────────────
print(df.info())          # dtypes + missing values
print(df.describe())      # statistical summary

# ── Select & filter ──────────────────────────────────────
revenue_col = df["Revenue"]                       # single column
high_sales  = df[df["Revenue"] > 10000]            # filter rows

# ── Group & aggregate ────────────────────────────────────
monthly = df.groupby("Month")["Revenue"].sum()
print(monthly)

# ── Missing values ───────────────────────────────────────
print(df.isnull().sum())                    # count per column

df = df.dropna()                              # drop rows with NaN
df["Age"].fillna(df["Age"].mean(), inplace=True)  # fill with mean

# ── Duplicates ───────────────────────────────────────────
print(df.duplicated().sum())                # count duplicates
df = df.drop_duplicates()                    # remove them

# ── Data type fixes ──────────────────────────────────────
df["Date"] = pd.to_datetime(df["Date"])    # string → datetime
df["Revenue"] = df["Revenue"].astype(float) # object → float

# ── Outlier detection (IQR method) ───────────────────────
Q1, Q3  = df["Revenue"].quantile([0.25, 0.75])
IQR     = Q3 - Q1
df      = df[(df["Revenue"] >= Q1 - 1.5*IQR) &
              (df["Revenue"] <= Q3 + 1.5*IQR)]

import matplotlib.pyplot as plt
import seaborn as sns

# ── Line chart ───────────────────────────────────────────
plt.plot(df["Month"], df["Revenue"], color="#6FB3F2", linewidth=2)
plt.xlabel("Month")
plt.ylabel("Revenue ($)")
plt.title("Monthly Revenue Trend")
plt.tight_layout()
plt.show()

# ── Distribution (Seaborn) ───────────────────────────────
sns.histplot(df["Revenue"], bins=30, kde=True)
plt.title("Revenue Distribution")
plt.show()

# ── Correlation heatmap ──────────────────────────────────
sns.heatmap(df.corr(), annot=True, cmap="Blues", fmt=".2f")
plt.title("Feature Correlation Matrix")
plt.show()

from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_squared_error, r2_score
from sklearn.preprocessing import StandardScaler

# ── Features & target ────────────────────────────────────
X = df[["Marketing_Spend", "Store_Count"]]
y = df["Revenue"]

# ── Scale features ───────────────────────────────────────
scaler = StandardScaler()
X_scaled = scaler.fit_transform(X)

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

# ── Train ────────────────────────────────────────────────
model = LinearRegression()
model.fit(X_train, y_train)

# ── Evaluate ─────────────────────────────────────────────
preds = model.predict(X_test)
print(f"MSE: {mean_squared_error(y_test, preds):,.2f}")   # lower = better
print(f"R²:  {r2_score(y_test, preds):.4f}")              # 1.0 = perfect