ch01

Author: Y1ran

Diff for: Iris_test/__init__.py

@@ -0,0 +1 @@
+#

Diff for: Iris_test/__main__.py

@@ -0,0 +1,34 @@
+# -*- coding: utf-8 -*-
+"""
+Created on Wed Aug  1 17:07:30 2018
+
+@author: Administrator
+"""
+
+import pandas as pd
+from sklearn.datasets import load_iris
+from sklearn.model_selection import train_test_split
+from sklearn.neighbors import KNeighborsClassifier
+
+if __name__ == '__main__':
+    iris_data = load_iris()
+    print(iris_data.keys())
+    
+    print(iris_data['target_names'],iris_data['data'])
+    
+    X_train, X_test, y_train, y_test = train_test_split(
+            iris_data['data'], iris_data['target'],random_state=0)
+    
+    print(X_train.shape,y_train.shape)
+    
+    iris_data_df = pd.DataFrame(X_train, columns=iris_data.feature_names)
+    scatter = pd.scatter_matrix(iris_data_df, c=y_train,figsize=(15,15),
+                                marker='o', hist_kwds={'bins':20},s=60,
+                                alpha=0.8)
+    
+    knn = KNeighborsClassifier(n_neighbors=1)
+    knn.fit(X_train,y_train)
+    
+    y_pred = knn.predict(X_test)
+    print("test score is :{:.2f}".format(knn.score(X_test,y_test)))
+    

Diff for: Supervised_learn/KNN.py

@@ -0,0 +1,27 @@
+# -*- coding: utf-8 -*-
+"""
+Created on Wed Aug  1 17:39:03 2018
+
+@author: Administrator
+"""
+import mglearn
+import pandas as pd
+from sklearn.datasets import load_iris
+from sklearn.model_selection import train_test_split
+from sklearn.neighbors import KNeighborsClassifier
+
+
+def Knn_clf(k):
+    mglearn.plots.plot_knn_classification(n_neighbors=k)
+    X, y = mglearn.datasets.make_forge()
+    
+    X_train, X_test, y_train, y_test = train_test_split(
+                X, y ,random_state=0)
+    clf = KNeighborsClassifier(n_neighbors=k)
+    
+    clf.fit(X_train,y_train)
+    print("test accuracy: {:.2f}".format(clf.score(X_test, y_test)))
+    
+def Knn_reg(k):
+    mglearn.plots.plot_knn_regression(n_neighbors=k)
+    

Diff for: Supervised_learn/Linear_reg.py

@@ -0,0 +1,39 @@
+# -*- coding: utf-8 -*-
+"""
+Created on Thu Aug  2 16:24:58 2018
+
+@author: Administrator
+"""
+from sklearn.linear_model import LinearRegression
+from sklearn.linear_model import Ridge
+from sklearn.linear_model import Lasso
+
+import mglearn
+import numpy as np
+
+def Linear_reg():
+    X, y = mglearn.datasets.load_extended_boston()
+    
+    X_train, X_test, y_train, y_test = train_test_split(
+                X, y ,random_state=0)
+    
+    lr = LinearRegression().fit(X_train,y_train)
+    print("lr.coef: {}, bias: {}".format(lr.coef_, lr.intercept_))
+    print("lr.test: {:.2f}".format(lr.score(X_test,y_test)))
+
+def Rigde_reg():
+    X, y = mglearn.datasets.load_extended_boston()
+    
+    X_train, X_test, y_train, y_test = train_test_split(
+                X, y ,random_state=0)
+    ridge = Ridge(alpha=0.5).fit(X_train,y_train)
+    print("lr.test: {:.2f}".format(ridge.score(X_test,y_test)))
+
+def Lasso_reg():
+    X, y = mglearn.datasets.load_extended_boston()
+    
+    X_train, X_test, y_train, y_test = train_test_split(
+                X, y ,random_state=0)
+    lasso = Lasso(alpha=0.0015, max_iter=100000).fit(X_train,y_train)
+    print("lr.test: {:.2f}".format(lasso.score(X_test,y_test)))
+    print("the number of features is:" , np.sum(lasso.coef_ != 0))

Diff for: Supervised_learn/__init__.py

@@ -0,0 +1 @@
+#

Diff for: Supervised_learn/__main__.py

@@ -0,0 +1,32 @@
+# -*- coding: utf-8 -*-
+"""
+Created on Wed Aug  1 17:38:57 2018
+
+@author: Administrator
+"""
+from load_data import *
+from knn import *
+import matplotlib.pyplot as plt
+
+if __name__ == '__main__':
+    
+    cancer, bos = Create_data()
+    X_train, X_test, y_train, y_test = train_test_split(
+                cancer.data, cancer.target , stratify=cancer.target
+                , random_state=0)
+    train_acurracy = []
+    test_acurracy = []
+    
+    setting = range(1,10)
+    
+    for k in setting:
+        clf = KNeighborsClassifier(n_neighbors=k)
+        clf.fit(X_train, y_train)
+        
+        train_acurracy.append(clf.score(X_train, y_train))
+        test_acurracy.append(clf.score(X_test, y_test))
+    
+    plt.plot(setting, train_acurracy,label='train')
+    plt.plot(setting, test_acurracy,label='test')
+    plt.legend()
+    

Diff for: Supervised_learn/load_data.py

@@ -0,0 +1,21 @@
+# -*- coding: utf-8 -*-
+"""
+Created on Wed Aug  1 17:38:47 2018
+
+@author: Administrator
+"""
+
+import mglearn
+import matplotlib.pyplot as plt
+from sklearn.datasets import load_breast_cancer, load_boston
+
+def Create_data():
+    X, y = mglearn.datasets.make_forge()
+    
+    #mglearn.discrete_scatter(X[:,0], X[:,1],y)
+    plt.legend(["Class 0", "Class 1"], loc=4)    
+    
+    cancer = load_breast_cancer()
+    print("cancer key: \n{}".format(cancer.keys()))
+    boston = load_boston()
+    return cancer, boston