update3

README.md

@@ -313,5 +313,176 @@ plt.show()
 
 </div>
 
+<summary>Gradient Boosting - Classification</summary>
+<div markdown="1">
+  
+````python
+    from sklearn.datasets import make_hastie_10_2
+    from sklearn.ensemble import GradientBoostingClassifier
+    import matplotlib.pyplot as plt
+
+    X, y = make_hastie_10_2(random_state=0)
+    X_train, X_test = X[:2000], X[2000:]
+    y_train, y_test = y[:2000], y[2000:]
+    print(X.shape, y.shape)
+    print(X[0:5,:])
+    print(y[0:5])
+
+    clf = GradientBoostingClassifier(n_estimators=100, learning_rate=0.1, max_depth=1, random_state=0)
+    clf.fit(X_train, y_train)
+    print('Accuracy score (training): {0:.3f}'.format(clf.score(X_train, y_train)))
+    print('Accuracy score (testing): {0:.3f}'.format(clf.score(X_test, y_test)))
+````
+
+</div>
+
+<summary>Result</summary>
+<div markdown="1">
+
+````planetext
+    (12000, 10) (12000,)
+    [[ 1.76405235  0.40015721  0.97873798  2.2408932   1.86755799 -0.97727788
+    0.95008842 -0.15135721 -0.10321885  0.4105985 ]
+    [ 0.14404357  1.45427351  0.76103773  0.12167502  0.44386323  0.33367433
+    1.49407907 -0.20515826  0.3130677  -0.85409574]
+    [-2.55298982  0.6536186   0.8644362  -0.74216502  2.26975462 -1.45436567
+    0.04575852 -0.18718385  1.53277921  1.46935877]
+    [ 0.15494743  0.37816252 -0.88778575 -1.98079647 -0.34791215  0.15634897
+    1.23029068  1.20237985 -0.38732682 -0.30230275]
+    [-1.04855297 -1.42001794 -1.70627019  1.9507754  -0.50965218 -0.4380743
+    -1.25279536  0.77749036 -1.61389785 -0.21274028]]
+    [ 1. -1.  1. -1.  1.]
+    Accuracy score (training): 0.879
+    Accuracy score (testing): 0.819
+````
+
+</div>
+
+<summary>XGBoosting - Regression</summary>
+<div markdown="1">
+  
+````python
+    import numpy as np
+    import pandas as pd
+    from sklearn.datasets import load_boston
+    from sklearn.metrics import mean_squared_error
+    from sklearn.model_selection import train_test_split
+    import xgboost as xgb
+
+    boston = load_boston()
+    data = pd.DataFrame(boston.data)
+    data.columns = boston.feature_names
+    data['PRICE'] = boston.target
+    print(data.head())
+    X, y = data.iloc[:,:-1], data.iloc[:,-1]
+
+    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=123)
+    xg_reg = xgb.XGBRegressor(objective='reg:squarederror', colsample_bytree=0.3, learning_rate=0.1, max_depth=5, alpha=10, n_estimators=10)
+    xg_reg.fit(X_train, y_train)
+    preds = xg_reg.predict(X_test)
+    rmse = np.sqrt(mean_squared_error(y_test, preds))
+    print('RMSE: %f' % (rmse))
+````
+
+</div>
+
+<summary>Result</summary>
+<div markdown="1">
+
+````planetext
+        CRIM    ZN  INDUS  CHAS    NOX     RM   AGE     DIS  RAD    TAX   
+    0  0.00632  18.0   2.31   0.0  0.538  6.575  65.2  4.0900  1.0  296.0  
+    1  0.02731   0.0   7.07   0.0  0.469  6.421  78.9  4.9671  2.0  242.0   
+    2  0.02729   0.0   7.07   0.0  0.469  7.185  61.1  4.9671  2.0  242.0   
+    3  0.03237   0.0   2.18   0.0  0.458  6.998  45.8  6.0622  3.0  222.0   
+    4  0.06905   0.0   2.18   0.0  0.458  7.147  54.2  6.0622  3.0  222.0   
+
+    PTRATIO       B  LSTAT  PRICE  
+    0     15.3  396.90   4.98   24.0  
+    1     17.8  396.90   9.14   21.6  
+    2     17.8  392.83   4.03   34.7  
+    3     18.7  394.63   2.94   33.4  
+    4     18.7  396.90   5.33   36.2  
+    RMSE: 10.423243
+````
+
+</div>
+
+
+<summary>LightGBM</summary>
+<div markdown="1">
+  
+````python
+    from lightgbm import LGBMClassifier, LGBMRegressor
+    from lightgbm import plot_importance, plot_metric, plot_tree
+    from sklearn.datasets import load_iris
+    from sklearn.model_selection import train_test_split
+    from sklearn.model_selection import cross_validate
+
+    iris = load_iris()
+    X_train, X_test, y_train, y_test = train_test_split(iris.data, iris.target, test_size=0.2, random_state=123)
+    lgbmc = LGBMClassifier(n_estimators=400)
+    evals = [(X_test, y_test)]
+    lgbmc.fit(X_train, y_train, early_stopping_rounds=100, eval_metric='logloss', eval_set=evals, verbose=True)
+    preds = lgbmc.predict(X_test)
+
+    cross_val = cross_validate(
+        estimator=lgbmc,
+        X=iris.data, y=iris.target,
+        cv=5
+    )
+
+    print('avg fit time: {} (+/- {})'.format(cross_val['fit_time'].mean(), cross_val['fit_time'].std()))
+    print('avg fit time: {} (+/- {})'.format(cross_val['score_time'].mean(), cross_val['score_time'].std()))
+    print('avg fit time: {} (+/- {})'.format(cross_val['test_score'].mean(), cross_val['test_score'].std()))
+
+    plot_metric(lgbmc)
+    plot_importance(lgbmc, figsize=(10,12))
+    plot_tree(lgbmc, figsize=(28,14))
+````
+
+</div>
+
+<summary>Result</summary>
+<div markdown="1">
+
+````planetext
+    [1]	valid_0's multi_logloss: 0.95847
+    [2]	valid_0's multi_logloss: 0.832184
+    [3]	valid_0's multi_logloss: 0.731164
+    [4]	valid_0's multi_logloss: 0.641056
+    [5]	valid_0's multi_logloss: 0.571726
+    [6]	valid_0's multi_logloss: 0.507286
+    [7]	valid_0's multi_logloss: 0.454933
+    [8]	valid_0's multi_logloss: 0.410205
+    [9]	valid_0's multi_logloss: 0.372194
+    [10]	valid_0's multi_logloss: 0.333919
+    [11]	valid_0's multi_logloss: 0.310212
+    [12]	valid_0's multi_logloss: 0.282326
+    [13]	valid_0's multi_logloss: 0.257165
+    [14]	valid_0's multi_logloss: 0.240836
+    [15]	valid_0's multi_logloss: 0.225383
+    [16]	valid_0's multi_logloss: 0.211583
+    [17]	valid_0's multi_logloss: 0.199289
+    [18]	valid_0's multi_logloss: 0.186269
+    [19]	valid_0's multi_logloss: 0.171556
+    [20]	valid_0's multi_logloss: 0.168245
+    [21]	valid_0's multi_logloss: 0.161065
+    [22]	valid_0's multi_logloss: 0.151371
+    [23]	valid_0's multi_logloss: 0.148081
+    [24]	valid_0's multi_logloss: 0.143843
+    [25]	valid_0's multi_logloss: 0.140169
+    ...
+    [137]	valid_0's multi_logloss: 0.376748
+    avg fit time: 0.5514350891113281 (+/- 0.3701610138582717)
+    avg fit time: 0.010002517700195312 (+/- 0.009552237668971902)
+    avg fit time: 0.9600000000000002 (+/- 0.04898979485566355)
+````
+
+![result](./images/11_4.png)
+![result](./images/11_5.png)
+![result](./images/11_6.png)
+
+</div>
 
 </details>