1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97
| import pandas as pd import numpy as np import itertools
from sklearn.model_selection import train_test_split from sklearn.metrics import confusion_matrix
from sklearn.ensemble import IsolationForest
from sklearn.externals import joblib
import matplotlib.pyplot as plt
def plot_confusion_matrix(cm, classes, normalize=False, title='Confusion matrix', cmap=plt.cm.Blues): if normalize: cm = cm.astype('float') / cm.sum(axis=1)[:, np.newaxis] print("Normalized confusion matrix") else: print('Confusion matrix, without normalization')
print(cm)
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)
fmt = '.2f' if normalize else 'd' thresh = cm.max() / 2. for i, j in itertools.product(range(cm.shape[0]), range(cm.shape[1])): plt.text(j, i, format(cm[i, j], fmt), horizontalalignment="center", color="white" if cm[i, j] > thresh else "black")
plt.tight_layout() plt.ylabel('True label') plt.xlabel('Predicted label')
DROPCOLUMS = ["id","label","date"]
train_data = pd.read_csv('../data/atec_anti_fraud_train.csv')
train_data = train_data.fillna(0)
known = train_data[train_data['label'] != -1]
knownlabel = known['label'] train, test = train_test_split(known, test_size=0.2, random_state=42)
cols = [c for c in DROPCOLUMS if c in train.columns] x_train = train.drop(cols,axis=1)
cols = [c for c in DROPCOLUMS if c in test.columns] x_test = test.drop(cols,axis=1)
y_train = train['label'] y_test = test['label']
clf = IsolationForest()
clf.fit(x_train)
y_pre = clf.predict(x_test)
ny_pre = np.asarray(y_pre) ny_pre[ny_pre==1] = 0 ny_pre[ny_pre==-1] = 1
ny_test = np.asarray(y_test)
class_names = ['normal','dangours'] cnf_matrix = confusion_matrix(ny_test, ny_pre)
np.set_printoptions(precision=2)
plt.figure() plot_confusion_matrix(cnf_matrix, classes=class_names, title='Confusion matrix, without normalization')
plt.figure() plot_confusion_matrix(cnf_matrix, classes=class_names, normalize=True, title='Normalized confusion matrix') plt.show()
|