مقدّمة Machine Learning: من الصفر إلى أول نموذج

pip install scikit-learn pandas numpy matplotlib

from sklearn.datasets import load_iris
import pandas as pd

data = load_iris()
df = pd.DataFrame(data.data, columns=data.feature_names)
df['species'] = [data.target_names[i] for i in data.target]
print(df.head())

from sklearn.model_selection import train_test_split

X = data.data        # الميزات
y = data.target      # الإجابات

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

print(f"Training: {len(X_train)}")   # 120
print(f"Test: {len(X_test)}")         # 30

from sklearn.ensemble import RandomForestClassifier

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

# التنبؤ
predictions = model.predict(X_test)

from sklearn.metrics import accuracy_score, classification_report

print(f"الدقة: {accuracy_score(y_test, predictions):.2%}")
print(classification_report(y_test, predictions, target_names=data.target_names))

# زهرة جديدة: [طول الكأس, عرضه, طول البتلة, عرضها]
new_flower = [[5.1, 3.5, 1.4, 0.2]]
prediction = model.predict(new_flower)
print(data.target_names[prediction[0]])   # setosa

import pandas as pd
from sklearn.datasets import fetch_california_housing
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_squared_error, r2_score
import numpy as np

# 1. تحميل البيانات
data = fetch_california_housing()
X, y = data.data, data.target

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

# 3. Normalization
scaler = StandardScaler()
X_train_scaled = scaler.fit_transform(X_train)
X_test_scaled = scaler.transform(X_test)

# 4. تدريب
model = LinearRegression()
model.fit(X_train_scaled, y_train)

# 5. تقييم
predictions = model.predict(X_test_scaled)
rmse = np.sqrt(mean_squared_error(y_test, predictions))
r2 = r2_score(y_test, predictions)

print(f"RMSE: {rmse:.3f}")
print(f"R²: {r2:.3f}")    # كم % من التباين يفسّره النموذج

from sklearn.model_selection import cross_val_score
scores = cross_val_score(model, X, y, cv=5)
print(f"الدقة: {scores.mean():.2%} ± {scores.std():.2%}")

from sklearn.model_selection import GridSearchCV

param_grid = {
    "n_estimators": [50, 100, 200],
    "max_depth": [None, 10, 20],
}

grid = GridSearchCV(RandomForestClassifier(), param_grid, cv=3)
grid.fit(X_train, y_train)
print(grid.best_params_)

import matplotlib.pyplot as plt

plt.scatter(df['sepal length (cm)'], df['sepal width (cm)'],
            c=data.target, cmap='viridis')
plt.xlabel('Sepal Length')
plt.ylabel('Sepal Width')
plt.colorbar(label='Species')
plt.show()

import joblib

joblib.dump(model, "iris_model.pkl")

# لاحقاً
loaded = joblib.load("iris_model.pkl")
loaded.predict(new_flower)