09

import pandas as pd
from sklearn.metrics import classification_report
from imblearn.over_sampling import SMOTE
import numpy as np
from sklearn.preprocessing import StandardScaler
from sklearn.model_selection import train_test_split
import matplotlib.pyplot as plt
import itertools
from xgboost.sklearn import XGBClassifier
from sklearn import metrics

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)



X_train, X_test, y_train, y_test =  train_test_split(X, y, test_size=0.3, random_state=80)



sc = StandardScaler()
sc.fit(X_train)
X_test = sc.transform(X_test)
X_train = sc.transform(X_train)

sm = SMOTE( kind='borderline1')
X_train, y_train = sm.fit_sample(X_train, y_train)

xgb = XGBClassifier(max_depth=10, n_estimators=200)
xgb.fit(X_train, y_train)





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 label')
    plt.xlabel('Predicted label')


cnf_matrix = metrics.confusion_matrix(y_test,xgb.predict(X_test))
target_names = ['0', '1']
plot_confusion_matrix(cnf_matrix, classes=target_names)

plt.show()
print(classification_report(y_test, xgb.predict(X_test)))
accuracy = metrics.accuracy_score(y_test, xgb.predict(X_test))
print(accuracy)