app_v1.py

from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score, confusion_matrix, classification_report
import matplotlib.pyplot as plt
import seaborn as sns
import numpy as np
import pandas as pd

from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler, LabelEncoder
from sklearn.ensemble import RandomForestClassifier

# Step 1: Generate synthetic dataset
np.random.seed(42)
n_records = 10000

data = {
    'pe_ratio': np.random.uniform(5, 50, n_records),
    'de_ratio': np.random.uniform(0.1, 3.0, n_records),
    'roe': np.random.uniform(5, 40, n_records),
    'market_cap': np.random.uniform(500, 100000, n_records),
    'dividend_yield': np.random.uniform(0.5, 5.0, n_records),
    'stock_rating': np.random.choice(['Buy', 'Hold', 'Sell'], n_records, p=[0.4, 0.4, 0.2])
}

df = pd.DataFrame(data)

# Step 2: Prepare data
X = df.drop('stock_rating', axis=1)
y = df['stock_rating']

# Step 3: Encode target
le = LabelEncoder()
y_encoded = le.fit_transform(y)

# Step 4: Train/test split (stratified)
X_train, X_test, y_train, y_test = train_test_split(
    X, y_encoded, test_size=0.2, random_state=42, stratify=y_encoded
)

# Step 5: Feature scaling
scaler = StandardScaler()
X_train_scaled = scaler.fit_transform(X_train)
X_test_scaled = scaler.transform(X_test)

# Step 6: Train model
model = RandomForestClassifier(random_state=42)
model.fit(X_train_scaled, y_train)

# Step 7️ Predict using your trained model
y_pred = model.predict(X_test_scaled)

# Step 8️ Inverse transform using correct label encoder
y_test_labels = le.inverse_transform(y_test)
y_pred_labels = le.inverse_transform(y_pred)

# Step 9️ Print basic metrics
print("✅ Accuracy:", accuracy_score(y_test_labels, y_pred_labels))
print("✅ Precision:", precision_score(y_test_labels, y_pred_labels, average='weighted'))
print("✅ Recall:", recall_score(y_test_labels, y_pred_labels, average='weighted'))
print("✅ F1 Score:", f1_score(y_test_labels, y_pred_labels, average='weighted'))

# Step 10️ Detailed breakdown per class
print("\n📊 Classification Report:")
print(classification_report(y_test_labels, y_pred_labels))

# Step 11️ Confusion Matrix
cm = confusion_matrix(y_test_labels, y_pred_labels, labels=le.classes_)

plt.figure(figsize=(6, 5))
sns.heatmap(cm, annot=True, fmt="d", cmap="Blues",
            xticklabels=le.classes_,
            yticklabels=le.classes_)
plt.xlabel("Predicted Label")
plt.ylabel("True Label")
plt.title("📉 Confusion Matrix")
plt.show()