File size: 4,249 Bytes
b2b32ab | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 | import gradio as gr
import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler, LabelEncoder
import xgboost as xgb
from sklearn.metrics import (
accuracy_score, precision_score, recall_score, f1_score,
confusion_matrix, classification_report
)
import seaborn as sns
import matplotlib.pyplot as plt
def train_and_evaluate_model():
# 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
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 using XGBoost
model = xgb.XGBClassifier(random_state=42, use_label_encoder=False, eval_metric='mlogloss')
model.fit(X_train_scaled, y_train)
# Step 7: Predict
y_pred = model.predict(X_test_scaled)
# Step 8: Decode labels
y_test_labels = le.inverse_transform(y_test)
y_pred_labels = le.inverse_transform(y_pred)
# Step 9: Metrics
acc = accuracy_score(y_test_labels, y_pred_labels)
prec = precision_score(y_test_labels, y_pred_labels, average='weighted', zero_division=0)
rec = recall_score(y_test_labels, y_pred_labels, average='weighted', zero_division=0)
f1 = f1_score(y_test_labels, y_pred_labels, average='weighted', zero_division=0)
# Step 10: Create Classification Report as DataFrame (with zero_division fix)
report_dict = classification_report(y_test_labels, y_pred_labels, output_dict=True, zero_division=0)
report_df = pd.DataFrame(report_dict).transpose().round(2)
# Step 11: Plot classification report as table with grid
fig, ax = plt.subplots(figsize=(8, 4))
ax.axis('off')
tbl = ax.table(
cellText=report_df.values,
colLabels=report_df.columns,
rowLabels=report_df.index,
cellLoc='center',
loc='center'
)
tbl.auto_set_font_size(False)
tbl.set_fontsize(10)
tbl.scale(1.2, 1.2)
for key, cell in tbl.get_celld().items():
cell.set_linewidth(0.8)
cr_path = "classification_report.png"
plt.savefig(cr_path, bbox_inches='tight')
plt.close()
# Step 12: 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")
plt.ylabel("Actual")
plt.title("Confusion Matrix")
cm_path = "confusion_matrix.png"
plt.savefig(cm_path, bbox_inches='tight')
plt.close()
# Step 13: Return outputs
output = f"""
### ✅ Evaluation Metrics:
- **Accuracy:** {acc:.2f}
- **Precision:** {prec:.2f}
- **Recall:** {rec:.2f}
- **F1 Score:** {f1:.2f}
"""
return output, cr_path, cm_path
# Gradio Interface
with gr.Blocks() as demo:
gr.Markdown("## 🧠 Stock Rating Prediction Model Evaluation")
gr.Markdown("Click the button below to train the model on synthetic stock data and evaluate its performance.")
eval_btn = gr.Button("Run Model Evaluation")
output_md = gr.Markdown()
report_img = gr.Image(type="filepath", label="📊 Classification Report")
cm_img = gr.Image(type="filepath", label="📉 Confusion Matrix")
eval_btn.click(fn=train_and_evaluate_model,
outputs=[output_md, report_img, cm_img])
demo.launch()
|