10

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import itertools
from sklearn.model_selection import train_test_split
from sklearn import tree
from sklearn.metrics import classification_report
from sklearn.metrics import confusion_matrix
from dtreeplt import dtreeplt



def plot_confusion_matrix(cm, classes,
                          normalize=False,
                          title='Confusion matrix',
                          cmap=plt.cm.Blues):
    """
    This function prints and plots the confusion matrix.
    Normalization can be applied by setting `normalize=True`.
    """
    plt.figure(figsize = (5, 5))
    plt.imshow(cm, interpolation='nearest', cmap=cmap)
    plt.title(title)
    plt.colorbar()
    tick_marks = np.arange(len(classes))
    plt.xticks(tick_marks, classes, rotation=45)
    plt.yticks(tick_marks, classes)

    if normalize:
        cm = cm.astype('float') / cm.sum(axis=1)[:, np.newaxis]
        print("Normalized confusion matrix")
    else:
        print('Confusion matrix, without normalization')

    print(cm)

    thresh = cm.max() / 2.
    for i, j in itertools.product(range(cm.shape[0]), range(cm.shape[1])):
        plt.text(j, i, cm[i, j],
                 horizontalalignment="center",
                 color="white" if cm[i, j] > thresh else "black")

    plt.tight_layout()
    plt.ylabel('True')
    plt.xlabel('Predicted')


#讀入資料
AllData = pd.read_csv('all_data.csv')


CleanData = AllData.dropna()
CleanData = CleanData.reset_index(drop=True)
CleanData = CleanData.drop('mdate', axis = 1)
CleanData = CleanData.drop('pmkt', axis = 1)

X = CleanData.drop('Y', axis = 1)

y = CleanData['Y']
y = y.astype(int)
#切分資料(70%訓練、30%測試)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.3,
                                                    random_state=12345)

#建立分類器
clf = tree.DecisionTreeClassifier(criterion = 'gini', max_depth = 5)
clf.fit(X_train, y_train)




#混淆矩陣
cnf_matrix = confusion_matrix(y_test, clf.predict(X_test))
target_names=['0', '1']
plot_confusion_matrix(cnf_matrix, classes =target_names,
                      title='Confusion matrix')
plt.show()
print(confusion_matrix(y_test,clf.predict(X_test)))

#精準度、召回率
print(classification_report(y_test, clf.predict(X_test)))

#印出正確率
from sklearn import metrics
accuracy = metrics.accuracy_score(y_test, clf.predict(X_test))
print(accuracy)

#特徵重要性

feature_names= X.keys().tolist()
clf.feature_importances_.tolist()
a=clf.feature_importances_.tolist()

df = pd.DataFrame({'feature':feature_names,
                   'feature_importance':clf.feature_importances_.tolist()})
df = df.sort_values(by=['feature_importance'], ascending=False).reset_index(drop=True)

def autolabel(rects):
    for rect in rects:
        height = rect.get_height()
        plt.text(rect.get_x()+rect.get_width()/2., 1.02*height, '%f'%float(height),
                 ha='center', va='bottom')

plt.style.use('ggplot')
fig = plt.figure(figsize=(8, 4))
plt.rcParams['font.family'] = 'DFKai-sb'  #標楷體
gini = plt.bar(df.index, df['feature_importance'], align='center')
plt.xlabel('Feature')  #X軸名稱
plt.ylabel('Feature Importance')  #Y軸名稱
plt.xticks(df.index, df['feature'])  #X軸項目名稱

autolabel(gini)

plt.show()

dtree = dtreeplt(model = clf,feature_names = X.keys().tolist(), target_names = y.keys().tolist())
fig = dtree.view()
fig.savefig('output.png')