Upload bmw (1).py

bmw (1).py

@@ -0,0 +1,283 @@
+# -*- coding: utf-8 -*-
+"""bmw.ipynb
+
+Automatically generated by Colab.
+
+Original file is located at
+    https://colab.research.google.com/drive/1Z-qv95gP_ABNRU7BiTH6jASxVMgk2BQZ
+"""
+
+import pandas as pd
+import numpy as np
+import matplotlib.pyplot as plt
+import seaborn as sns
+
+dataset = pd.read_csv('/content/BMW_Car_Sales_Classification.csv')
+dataset.head()
+
+dataset['Model'].unique()
+
+dataset.isnull().sum()
+
+dataset.info()
+
+from sklearn.preprocessing import LabelEncoder
+le = LabelEncoder()
+
+dataset['Model'] = le.fit_transform(dataset['Model'])
+
+dataset['Region'] = le.fit_transform(dataset['Region'])
+
+dataset['Color'] = le.fit_transform(dataset['Color'])
+
+dataset['Fuel_Type'] = le.fit_transform(dataset['Fuel_Type'])
+
+dataset['Transmission'] = le.fit_transform(dataset['Transmission'])
+
+dataset['Sales_Classification'] = le.fit_transform(dataset['Sales_Classification'])
+
+dataset.head(5)
+
+x = dataset.iloc[:,:-1]
+y = dataset.iloc[:,-1]
+
+x
+
+y
+
+dataset['Model'].describe()
+
+sns.barplot(x='Model', y='Year', data=dataset)
+plt.show()
+
+sns.countplot(x='Model', data=dataset)
+plt.show()
+
+sns.distplot(dataset['Year'])
+plt.show()
+
+from sklearn.model_selection import train_test_split
+x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.2, random_state=42)
+
+from sklearn.preprocessing import StandardScaler
+sc = StandardScaler()
+
+x_train_scaled = sc.fit_transform(x_train)
+x_test_scaled = sc.transform(x_test)
+
+x_train = pd.DataFrame(x_train_scaled, columns=x_train.columns)
+x_test = pd.DataFrame(x_test_scaled, columns=x_test.columns)
+
+x_train
+
+x_test
+
+from sklearn.linear_model import LogisticRegression
+from sklearn.metrics import accuracy_score, classification_report, confusion_matrix
+from sklearn.tree import DecisionTreeClassifier
+from sklearn.ensemble import RandomForestClassifier
+
+lg = LogisticRegression()
+lg.fit(x_train, y_train)
+
+lg.score(x_train, y_train)*100,lg.score(x_test, y_test)*100
+
+y_pred_lg = lg.predict(x_test)
+
+y_pred_lg
+
+dt = DecisionTreeClassifier()
+dt.fit(x_train, y_train)
+
+dt.score(x_train, y_train)*100,dt.score(x_test, y_test)*100
+
+y_pred = dt.predict(x_test)
+
+y_pred
+
+rg = RandomForestClassifier(n_estimators=5)
+rg.fit(x_train, y_train)
+
+rg.score(x_train, y_train)*100,rg.score(x_test, y_test)*100
+
+y_pred_rg = rg.predict(x_test)
+y_pred_rg
+
+accuracy_score = accuracy_score(y_test, y_pred_rg)
+accuracy_score
+
+cr = classification_report(y_test, y_pred_rg)
+print(cr)
+
+cf = confusion_matrix(y_test, y_pred_rg)
+cf
+
+sns.heatmap(cf, annot=True)
+plt.xlabel('Predicted')
+plt.ylabel('Truth')
+plt.show()
+
+dataset_original = pd.read_csv('/content/BMW_Car_Sales_Classification.csv')
+
+label_encoders = {}
+for column in dataset_original.select_dtypes(include='object').columns:
+    if column != 'Sales_Classification':
+        le = LabelEncoder()
+        dataset_original[column] = le.fit_transform(dataset_original[column])
+        label_encoders[column] = le
+
+scaler = StandardScaler()
+x_train_scaled = scaler.fit_transform(x_train)
+new_data = pd.DataFrame([{
+    "Model": "X5",
+    "Year": 2023,
+    "Region": "North America",
+    "Color": "Black",
+    "Fuel_Type": "Diesel",
+    "Transmission": "Automatic",
+    "Engine_Size_L": 3.0,
+    "Mileage_KM": 25000,
+    "Price_USD": 55000,
+    "Sales_Volume": 120
+}])
+
+for column in new_data.select_dtypes(include='object').columns:
+    le = label_encoders[column]
+    new_data[column] = le.transform(new_data[column])
+
+new_data = new_data[x_train.columns]
+
+new_data_scaled = scaler.transform(new_data)
+
+display(new_data_scaled)
+
+# Convert the scaled numpy array back to a pandas DataFrame with the correct column names
+new_data_scaled_df = pd.DataFrame(new_data_scaled, columns=x_train.columns)
+
+# Make prediction using the trained RandomForestClassifier model (rg)
+predicted_class = rg.predict(new_data_scaled_df)
+
+# Interpret prediction by converting numerical prediction back to original class label
+# We need to re-fit a LabelEncoder for Sales_Classification to inverse transform
+le_sales = LabelEncoder()
+le_sales.fit(pd.read_csv('/content/BMW_Car_Sales_Classification.csv')['Sales_Classification'])
+predicted_class_label = le_sales.inverse_transform(predicted_class)
+
+# Display the predicted class label
+print(f"Predicted Sales Classification: {predicted_class_label[0]}")
+
+pd.DataFrame(predicted_class_label, columns=['Predicted_Sales_Classification'])
+
+from google.colab import userdata
+userdata.get('HF_WRITE')
+
+HF_WRITE = userdata.get('HF_WRITE')
+
+!git config --global credential.helper cache
+
+!hf auth login
+
+from huggingface_hub import notebook_login
+notebook_login()
+
+# Make sure git-lfs is installed (https://git-lfs.com)
+!git lfs install
+
+!git remote add origin https://huggingface.co/RRPATEL228/car_price
+
+# You'll be prompted for your HF credentials
+!git push -u origin main
+
+# Install the Hugging Face CLI
+!pip install -U "huggingface_hub[cli]"
+
+!hf auth login
+
+from huggingface_hub import HfApi, Repository
+import shutil, os
+
+username = "RRPATEL228"         # Replace with your HF username
+model_name = "car_price_model"      # Choose a model repo name
+
+# Create and clone the repo
+api = HfApi()
+repo_url = api.create_repo(name=model_name, exist_ok=True, repo_type="model")
+repo = Repository(local_dir="model-repo", clone_from=repo_url)
+
+# Copy your saved model and architecture file into the repo directory
+# Assuming you have saved your model as 'random_forest_model.joblib' in the 'car_price_model' directory
+model_path = os.path.join("car_price_model", "random_forest_model.joblib")
+if os.path.exists(model_path):
+    shutil.copy(model_path, "model-repo/random_forest_model.joblib")
+    print(f"Successfully copied {model_path} to model-repo/")
+else:
+    print(f"Error: Model file not found at {model_path}. Please ensure the model saving cell was run successfully.")
+
+
+# (Optional) Add a README.md with usage instructions
+with open("model-repo/README.md", "w") as f:
+    f.write("""
+# My Tabular Model
+
+This is a model trained on tabular data for car price sales classification.
+
+To load the model:
+
+
+
+from huggingface_hub import HfApi, Repository
+import shutil, os
+
+username = "RRPATEL228"         # Replace with your HF username
+model_name = "car_price_model"      # Choose a model repo name
+
+# Create and clone the repo
+api = HfApi()
+repo_url = api.create_repo(name=model_name, exist_ok=True, repo_type="model")
+repo = Repository(local_dir="model-repo", clone_from=repo_url)
+
+# Copy your saved model and architecture file into the repo directory
+# Assuming you have saved your model as 'random_forest_model.joblib' in the 'car_price_model' directory
+model_path = os.path.join("car_price_model", "random_forest_model.joblib")
+if os.path.exists(model_path):
+    shutil.copy(model_path, "model-repo/random_forest_model.joblib")
+    print(f"Successfully copied {model_path} to model-repo/")
+else:
+    print(f"Error: Model file not found at {model_path}. Please ensure the model saving cell was run successfully.")
+
+
+# (Optional) Add a README.md with usage instructions
+with open("model-repo/README.md", "w") as f:
+    f.write("""
+# My Tabular Model
+
+This is a model trained on tabular data for car price sales classification.
+
+To load the model:
+
+from huggingface_hub import HfApi, Repository
+import shutil, os
+
+username = "RRPATEL228"         # Replace with your HF username
+model_name = "car_price_model"      # Choose a model repo name
+
+# Create and clone the repo
+api = HfApi()
+repo_url = api.create_repo(model_name, exist_ok=True, repo_type="model")
+repo = Repository(local_dir="model-repo", clone_from=repo_url)
+
+# Copy your saved model and architecture file into the repo directory
+# Assuming you have saved your model as 'random_forest_model.joblib' in the 'car_price_model' directory
+model_path = os.path.join("car_price_model", "random_forest_model.joblib")
+if os.path.exists(model_path):
+    shutil.copy(model_path, "model-repo/random_forest_model.joblib")
+    print(f"Successfully copied {model_path} to model-repo/")
+else:
+    print(f"Error: Model file not found at {model_path}. Please ensure the model saving cell was run successfully.")
+
+# If you had a model architecture file (e.g., a Python script defining the model class), copy it here as well.
+# shutil.copy("model.py", "model-repo/model.py")
+
+# Removed the README.md writing section to avoid SyntaxError
+# You can manually add a README.md on Hugging Face Hub after uploading.
+