Upload 3 files

app.py

@@ -0,0 +1,100 @@
+# -*- coding: utf-8 -*-
+"""car_price.ipynb
+
+Automatically generated by Colab.
+
+Original file is located at
+    https://colab.research.google.com/drive/1rtMdlilQhGBozNcdxDeSkuEthtwAz7-L
+"""
+
+import pandas as pd
+import numpy as np
+import warnings
+warnings.filterwarnings('ignore')
+
+dataset = pd.read_csv('car.csv')
+df = dataset.copy()
+
+def other_values(df,col,n):
+  tc = df[col].value_counts()
+  ov = tc[tc<=n].index
+  df[col] = df[col].apply(lambda x: 'Other' if x in ov else x)
+
+def datacleanning(X):
+    X = X.drop_duplicates()
+    X.dropna(axis=0, inplace=True)
+    if 'Unnamed: 0' in X.columns:
+      X.drop('Unnamed: 0', axis=1, inplace=True)
+    other_values(X, 'Company Name', 100)
+    other_values(X, 'Model Name', 100)
+    other_values(X, 'Color', 170)
+    return X
+
+from sklearn.model_selection import train_test_split
+def train_test(df):
+        X=df.drop('Price',axis=1)
+        y=df['Price']
+        X_train,X_test,y_train,y_test = train_test_split(X,y,test_size=0.2,random_state=43)
+        return X_train,X_test,y_train,y_test
+
+def dummie(X_train,X_test):
+    X_train = pd.get_dummies(X_train,drop_first=True)
+    X_test = pd.get_dummies(X_test,drop_first=True)
+    return X_train,X_test
+
+def final_df(df):
+  df =datacleanning(df)
+  X_train,X_test,y_train,y_test = train_test(df)
+  X_train,X_test = dummie(X_train,X_test)
+  return df,X_train,X_test,y_train,y_test
+
+from sklearn.ensemble import HistGradientBoostingRegressor
+def model_fit(X_train,y_train):
+  hgb = HistGradientBoostingRegressor()
+  hgb.fit(X_train,y_train)
+  return hgb
+
+model = model_fit(X_train,y_train)
+
+!pip install streamlit
+
+df = pd.get_dummies(df,drop_first=True)
+
+import streamlit as st
+
+def price(companyName,modelName,modelYear,locaiton,mileage,engineType,engineCapacity,color,assembly,bodyType,transmissionType,registrationStatus):
+  input_data = pd.DataFrame({
+      'Company Name':[companyName],
+      'Model Name':[modelName],
+      'Model Year':[modelYear],
+      'Location':[locaiton],
+      'Mileage':[mileage],
+      'Engine Type':[engineType],
+      'Engine Capacity':[engineCapacity],
+      'Color':[color],
+      'Assembly':[assembly],
+      'Body Type':[bodyType],
+      'Transmission Type':[transmissionType],
+      'Registration Status':[registrationStatus]
+  })
+  prediction=model.predict(input_data)[0]
+  return prediction
+st.title('Car Price Prediction:car @yusufenes')
+st.write('Please Chose Car Specifications')
+companyName = st.selectbox('Company Name',df['Company Name'].unique())
+modelName = st.selectbox('Model Name',df[df['Company Name']==companyName]['Model Name'].unique())
+modelYear = st.selectbox('Model Year',df[(df['Company Name']==companyName)&(df['Model Name'] == modelName)]['Model Year'].unique())
+locaiton = st.selectbox('Location',df['Location'].unique())
+mileage = st.number_input('Mileage',df['Mileage'].min(),df['Mileage'].max())
+engineType = st.selectbox('Engine Type',df['Engine Type'].unique())
+engineCapacity = st.number_input('Engine Capacity',df['Engine Capacity'].min(),df['Engine Capacity'].max())
+color = st.selectbox('Color',df['Color'].unique())
+assembly = st.selectbox('Assembly',df['Assembly'].unique())
+bodyType = st.selectbox('Body Type',df['Body Type'].unique())
+transmissionType = st.selectbox('Transmission Type',df['Transmission Type'].unique())
+registrationStatus = st.radio('Registration Status',['Yes','No'])
+if st.button('Predict'):
+  pred=price(companyName,modelName,modelYear,locaiton,mileage,engineType,engineCapacity,color,assembly,bodyType,transmissionType,registrationStatus)
+  st.success(f'The predicted price is {pred} $')
+  st.balloons()
+

requirements.txt

@@ -0,0 +1,3 @@
+streamlit==1.31.1
+scikit-learn==1.4.1.post1
+pandas==2.1.0