# 1) Python + Pandas + EDA
import pandas as pd

df = pd.read_csv('penjualan.csv')
print(df.head())
print(df.describe())

# missing value
median = df['omzet'].median()
df['omzet'] = df['omzet'].fillna(median)

# groupby
ringkas = df.groupby('wilayah')['omzet'].sum()
print(ringkas)

# 2) Machine Learning sederhana
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score, confusion_matrix

X = df[['umur','pendapatan','frekuensi_beli']]
y = df['loyal']
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=.2)
model = RandomForestClassifier(random_state=42)
model.fit(X_train, y_train)
pred = model.predict(X_test)
print(accuracy_score(y_test, pred))
print(confusion_matrix(y_test, pred))

-- 3) SQL untuk analisis pelanggan
SELECT wilayah,
       COUNT(*) AS jumlah_pelanggan,
       AVG(omzet) AS rata_omzet,
       SUM(omzet) AS total_omzet
FROM transaksi
WHERE tanggal >= '2026-01-01'
GROUP BY wilayah
HAVING SUM(omzet) > 10000000
ORDER BY total_omzet DESC;

# 4) Time series: moving average
import pandas as pd

ts = pd.Series([10,12,13,18,21,20,25,29])
ma3 = ts.rolling(window=3).mean()
forecast_simple = ma3.iloc[-1]
print('Prediksi sederhana:', forecast_simple)