Machine Learning: تمرين شامل

# قالب سير عمل ML الشامل
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_absolute_error, r2_score

# الخطوة 1: التحميل والاستكشاف
df = pd.read_csv("sales_data.csv")
print(df.describe())

# الخطوة 2: التنظيف وإعداد الميزات
features = ["ad_spend", "traffic", "last_month_sales"]
target = "monthly_revenue"
df = df.dropna(subset=features + [target])

# الخطوة 3: تدريب خط الأساس
X_train, X_test, y_train, y_test = train_test_split(df[features], df[target], test_size=0.2)
model = LinearRegression().fit(X_train, y_train)
pred = model.predict(X_test)

# الخطوة 4: التقييم
print(f"R²: {r2_score(y_test, pred):.3f}, MAE: {mean_absolute_error(y_test, pred):.0f} USD")

import pandas as pd
import numpy as np

rng = np.random.default_rng(42)
n = 1000

df = pd.DataFrame({
    "date": pd.date_range("2023-01-01", periods=n, freq="D"),
    "ad_spend_k": rng.uniform(5, 100, n),
    "traffic_k": rng.uniform(10, 500, n),
    "category": rng.choice(["Electronics", "Clothing", "Food", "Books", "Home"], n),
    "is_promotion": rng.choice([0, 1], n, p=[0.8, 0.2]),
    "customer_count": rng.integers(50, 500, n),
})

# صيغة الإيرادات بعلاقات واقعية
df["revenue_k"] = (
    20
    + 0.6 * df["ad_spend_k"]
    + 0.08 * df["traffic_k"]
    + 0.5 * df["customer_count"]
    + 50 * df["is_promotion"]
    + rng.normal(0, 15, n)
)
df["revenue_k"] = df["revenue_k"].clip(lower=0)

# حقن بعض القيم المفقودة والقيم المتطرفة
missing_idx = rng.choice(n, size=50, replace=False)
df.loc[missing_idx[:25], "ad_spend_k"] = np.nan
df.loc[missing_idx[25:], "traffic_k"] = np.nan

outlier_idx = rng.choice(n, size=10, replace=False)
df.loc[outlier_idx, "revenue_k"] *= 5

print(f"Dataset shape: {df.shape}")
print(f"Missing values:\n{df.isnull().sum()}")
df.to_csv("salespredict_data.csv", index=False)

# Executed successfully

import pandas as pd
import numpy as np

df = pd.read_csv("salespredict_data.csv", parse_dates=["date"])

# نظرة عامة أساسية
print("=" * 50)
print("DATA OVERVIEW")
print("=" * 50)
print(f"Shape: {df.shape}")
print(f"\nDtypes:\n{df.dtypes}")
print(f"\nBasic Stats:\n{df.describe().round(2)}")
print(f"\nMissing Values:\n{df.isnull().sum()}")
print(f"\nCategory Distribution:\n{df['category'].value_counts()}")

=
DATA OVERVIEW
=

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

df = pd.read_csv("salespredict_data.csv", parse_dates=["date"])
sns.set_theme(style="whitegrid")

fig, axes = plt.subplots(2, 3, figsize=(18, 10))

# (1) توزيع الإيرادات
sns.histplot(df["revenue_k"], bins=40, kde=True, ax=axes[0, 0], color="#2196F3")
axes[0, 0].set_title("Revenue Distribution (thousand USD)")

# (2) الإيرادات حسب الفئة
sns.boxplot(data=df, x="category", y="revenue_k", ax=axes[0, 1], palette="Set2")
axes[0, 1].set_title("Revenue by Category")

# (3) تأثير العروض الترويجية
sns.barplot(data=df, x="is_promotion", y="revenue_k", ax=axes[0, 2], palette="Pastel1")
axes[0, 2].set_title("Promotion Effect on Revenue")

# (4) الإنفاق الإعلاني مقابل الإيرادات
axes[1, 0].scatter(df["ad_spend_k"], df["revenue_k"], alpha=0.3, s=10)
axes[1, 0].set_xlabel("Ad Spend (thousand USD)")
axes[1, 0].set_ylabel("Revenue (thousand USD)")
axes[1, 0].set_title("Ad Spend vs Revenue")

# (5) الزيارات مقابل الإيرادات
axes[1, 1].scatter(df["traffic_k"], df["revenue_k"], alpha=0.3, s=10, color="#4CAF50")
axes[1, 1].set_xlabel("Traffic (thousand)")
axes[1, 1].set_ylabel("Revenue (thousand USD)")
axes[1, 1].set_title("Traffic vs Revenue")

# (6) خريطة حرارية للارتباط
num_cols = ["ad_spend_k", "traffic_k", "customer_count", "is_promotion", "revenue_k"]
corr = df[num_cols].corr()
sns.heatmap(corr, annot=True, fmt=".2f", cmap="RdBu_r", ax=axes[1, 2], vmin=-1, vmax=1)
axes[1, 2].set_title("Feature Correlations")

plt.tight_layout()
plt.savefig("eda_overview.png", dpi=150)

# Executed successfully

import pandas as pd
import numpy as np

df = pd.read_csv("salespredict_data.csv", parse_dates=["date"])

# الخطوة 1: معالجة القيم المفقودة
print(f"Before cleaning: {len(df)} rows")
df = df.dropna(subset=["revenue_k"])  # حذف إذا كان الهدف مفقودًا
df["ad_spend_k"] = df["ad_spend_k"].fillna(df["ad_spend_k"].median())
df["traffic_k"] = df["traffic_k"].fillna(df["traffic_k"].median())

# الخطوة 2: إزالة القيم المتطرفة باستخدام IQR
def remove_outliers(df, col, factor=1.5):
    q1, q3 = df[col].quantile([0.25, 0.75])
    iqr = q3 - q1
    return df[(df[col] >= q1 - factor * iqr) & (df[col] <= q3 + factor * iqr)]

df = remove_outliers(df, "revenue_k")
print(f"After cleaning: {len(df)} rows")

# الخطوة 3: هندسة الميزات
df["month"] = df["date"].dt.month
df["day_of_week"] = df["date"].dt.dayofweek
df["is_weekend"] = (df["day_of_week"] >= 5).astype(int)

# الخطوة 4: ترميز الفئات
df_encoded = pd.get_dummies(df, columns=["category"], drop_first=True)

# الخطوة 5: اختيار الميزات
feature_cols = [c for c in df_encoded.columns if c not in ["date", "revenue_k"]]
X = df_encoded[feature_cols]
y = df_encoded["revenue_k"]

print(f"Features: {feature_cols}")
print(f"X shape: {X.shape}, y shape: {y.shape}")

# Functions defined successfully

from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
from sklearn.preprocessing import StandardScaler
from sklearn.pipeline import Pipeline
from sklearn.metrics import mean_absolute_error, mean_squared_error, r2_score
import numpy as np

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

# خط أنابيب خط الأساس
baseline = Pipeline([
    ("scaler", StandardScaler()),
    ("model", LinearRegression()),
])

baseline.fit(X_train, y_train)
y_pred = baseline.predict(X_test)

# تقييم شامل
mae = mean_absolute_error(y_test, y_pred)
rmse = np.sqrt(mean_squared_error(y_test, y_pred))
r2 = r2_score(y_test, y_pred)
mape = np.mean(np.abs((y_test - y_pred) / y_test)) * 100

print("=" * 50)
print("BASELINE MODEL EVALUATION")
print("=" * 50)
print(f"MAE:  {mae:.2f} thousand USD")
print(f"RMSE: {rmse:.2f} thousand USD")
print(f"R²:   {r2:.4f}")
print(f"MAPE: {mape:.1f}%")

=
BASELINE MODEL EVALUATION
=

import matplotlib.pyplot as plt
import numpy as np

fig, axes = plt.subplots(1, 2, figsize=(14, 5))

# (1) تشتت الفعلي مقابل المتنبأ به
axes[0].scatter(y_test, y_pred, alpha=0.5, s=20)
axes[0].plot([y_test.min(), y_test.max()], [y_test.min(), y_test.max()], "r--", lw=2)
axes[0].set_xlabel("Actual Revenue (thousand USD)")
axes[0].set_ylabel("Predicted Revenue (thousand USD)")
axes[0].set_title("Actual vs Predicted")

# (2) توزيع البواقي
residuals = y_test - y_pred
axes[1].hist(residuals, bins=30, edgecolor="white", color="#2196F3")
axes[1].axvline(x=0, color="red", linestyle="--")
axes[1].set_xlabel("Residual (thousand USD)")
axes[1].set_title("Residual Distribution")

plt.tight_layout()
plt.savefig("baseline_evaluation.png", dpi=150)

# Executed successfully