Upload app.py

app.py

@@ -0,0 +1,84 @@
+import numpy as np
+import pandas as pd
+import tensorflow as tf
+from sklearn.preprocessing import LabelEncoder, MinMaxScaler
+from keras.models import Sequential
+from keras.layers import Dense, Dropout
+from sklearn.model_selection import train_test_split
+import gradio as gr
+
+data = pd.read_csv('cars_raw.csv')
+
+le = LabelEncoder()
+data['Make'] = le.fit_transform(data['Make'])
+data['Model'] = le.fit_transform(data['Model'])
+data = data[data['Price'] != 'Not Priced']
+data["Price"] = data["Price"].str.replace("$", "").str.replace(",", "").astype(float)
+
+scaler = MinMaxScaler()
+data['Price'] = scaler.fit_transform(data['Price'].values.reshape(-1, 1))
+data = data.dropna()
+
+for col in data.select_dtypes(include=['category', 'object']).columns:
+    data[col] = le.fit_transform(data[col])
+
+for col in data.select_dtypes(include=['number']).columns:
+    data[col] = scaler.fit_transform(data[col].values.reshape(-1, 1))
+
+data = data.drop(columns=["Mileage", "SellerType", "VIN", "Stock#", "Drivetrain", "SellerName", "ConsumerReviews", "ExteriorStylingRating", "State", "Zipcode", "DealType"])
+X = data.drop('Price', axis=1)
+y = data['Price']
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)
+
+model = Sequential()
+model.add(Dense(128, input_shape=(X_train.shape[1],)))
+model.add(Dropout(0.3))
+model.add(Dense(64))
+model.add(Dropout(0.3))
+model.add(Dense(1))
+
+model.compile(optimizer='adam', loss='mean_squared_error')
+model.fit(X_train, y_train, epochs=100, batch_size=32, validation_data=(X_test, y_test))
+
+def predict_price(year, make, model_name, fuel_type, engine):
+    car_data = {
+        "Year": [year],
+        "Make": [make],
+        "Model": [model_name],
+        "FuelType": [fuel_type],
+        "Engine": [engine]
+    }
+
+    car_data_df = pd.DataFrame(car_data)
+    
+    needs_df = pd.concat([X, car_data_df], ignore_index=True)
+
+    for col in needs_df.select_dtypes(include=['category', 'object']).columns:
+        needs_df[col] = le.fit_transform(needs_df[col])
+
+    for col in needs_df.select_dtypes(include=['number']).columns:
+        needs_df[col] = scaler.fit_transform(needs_df[col].values.reshape(-1, 1))
+
+    result_df = needs_df.loc[[0]]
+    prediction = model.predict(result_df)
+
+    inverted_prediction = scaler.inverse_transform(prediction.reshape(-1, 1))
+    predicted_price = inverted_prediction[0][0]
+
+    return f'Предсказанная цена: ${predicted_price:.2f}'
+
+iface = gr.Interface(
+    fn=predict_price,
+    inputs=[
+        gr.inputs.Number(label="Год издания машины"),
+        gr.inputs.Textbox(label="Бренд машины"),
+        gr.inputs.Textbox(label="Модель машины"),
+        gr.inputs.Textbox(label="Тип топлива"),
+        gr.inputs.Textbox(label="Характеристики двигателя")
+    ],
+    outputs="text",
+    title="Предсказание цены автомобиля",
+    description="Введите характеристики автомобиля для предсказания его цены."
+)
+
+iface.launch(share=True)