Thitikarn/performancePrediction

1# -*- coding: utf-8 -*-2"""Untitled4.ipynb3 4Automatically generated by Colaboratory.5 6Original file is located at7    https://colab.research.google.com/drive/16mFkLf-4r0xA_PNjOfphDBQly-iVfhqk8"""9 10!pip install xgboost11!pip install scikit-learn12 13import pandas as pd14from sklearn.compose import ColumnTransformer15from sklearn.pipeline import Pipeline16from sklearn.preprocessing import OneHotEncoder, StandardScaler17from xgboost import XGBClassifier18 19X_train = pd.read_csv('exams.csv')20X_train21 22y_train = X_train.pop("race/ethnicity")23 24# Names of numerical features เชิงปริมาณ25num_col = X_train.select_dtypes(include=['int64', 'float64']).columns26# Names of categorical features เชิงคุณภาพ27cat_col = X_train.select_dtypes(include=['object', 'bool']).columns28 29preprocessor = ColumnTransformer([("scaler", StandardScaler(), num_col),30                                  ("onehot", OneHotEncoder(sparse=False), cat_col)])31 32model = Pipeline(steps=[('preprocessor', preprocessor),33                        ('classifier', XGBClassifier())])34 35from sklearn.preprocessing import LabelEncoder36 37label_encoder = LabelEncoder()38y_train_encoded = label_encoder.fit_transform(y_train)39 40model.fit(X_train, y_train_encoded)41 42import joblib43 44joblib.dump(model, 'model.joblib')45 46