import numpy as np # linear algebra
import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)
import matplotlib.pyplot as plt
%matplotlib inline
import seaborn as sns

pre_data = pd.read_csv("./preprocessed_data.csv")

data = pre_data.drop(columns=['Company_Name'])

data.head()

data.shape

(26531, 10)

### Get the train and test data-set, with and without sampling Train - Test data split without resampling

X = data.iloc[:, data.columns != 'Class'].values
y = data.iloc[:, data.columns == 'Class'].values

# Splitting the dataset into the Training set and Test set
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X,y,test_size = 0.3, random_state = 0)

print("Original number transactions train dataset: ", len(X_train))
print("Original number transactions test dataset: ", len(X_test))
print("Total number of transactions: ", len(X_train)+len(X_test))

Original number transactions train dataset:  18571
Original number transactions test dataset:  7960
Total number of transactions:  26531

# Number of data points in the minority class
number_records_fraud = len(data[data.Class == 1])
fraud_indices = np.array(data[data.Class == 1].index)
print(number_records_fraud)
#print(data[data.Class == 1])

6286

# Picking the indices of the normal classes
normal_indices = data[data.Class == 0].index

# Out of the indices we picked, randomly select "x" number (number_records_fraud)
#np.random.choice(). By using this, the numbers of fraud indices and non-fraud indices become equal. 
random_normal_indices = np.random.choice(a = normal_indices, size = number_records_fraud, replace = False)
random_normal_indices = np.array(random_normal_indices)

# Appending the 2 indices
under_sample_indices = np.concatenate([fraud_indices,random_normal_indices])
print(under_sample_indices)

[    0     1     2 ... 25853 17422  9442]

# Under sample dataset
under_sample_data = data.iloc[under_sample_indices,:]


X_undersample = under_sample_data.iloc[:, under_sample_data.columns != 'Class']
y_undersample = under_sample_data.iloc[:, under_sample_data.columns == 'Class']

# Showing ratio
print("Percentage of normal transactions: ", len(under_sample_data[under_sample_data.Class == 0])/len(under_sample_data))
print("Percentage of fraud transactions: ", len(under_sample_data[under_sample_data.Class == 1])/len(under_sample_data))
print("Total number of transactions in resampled data: ", len(under_sample_data))

Percentage of normal transactions:  0.5
Percentage of fraud transactions:  0.5
Total number of transactions in resampled data:  12572

# Undersampled dataset
X_train_undersample, X_test_undersample, y_train_undersample, y_test_undersample = train_test_split(X_undersample
                                                                                                   ,y_undersample
                                                                                                   ,test_size = 0.3
                                                                                                   ,random_state = 0)
print("")
print("Number transactions train dataset: ", len(X_train_undersample))
print("Number transactions test dataset: ", len(X_test_undersample))
print("Total number of transactions: ", len(X_train_undersample)+len(X_test_undersample))

Number transactions train dataset:  8800
Number transactions test dataset:  3772
Total number of transactions:  12572

# 从sklearn.preprocessing里导入数据标准化模块。
from sklearn.preprocessing import StandardScaler

#KNN
from sklearn.tree import DecisionTreeClassifier

# 从仍然需要对训练和测试的特征数据进行标准化。
ss = StandardScaler()
X_train_undersample = ss.fit_transform(X_train_undersample)
X_test_undersample = ss.transform(X_test_undersample)

# 初始化线性假设的支持向量机分类器LinearSVC。

#algorithm : {‘auto’, ‘ball_tree’, ‘kd_tree’, ‘brute’}

knn = DecisionTreeClassifier(criterion='entropy')
#进行模型训练
knn.fit(X_train_undersample, y_train_undersample)
# 利用训练好的模型对测试样本的数字类别进行预测，预测结果储存在变量y_predict中。
y_predict_undersample = knn.predict(X_test_undersample)

from sklearn.metrics import confusion_matrix,precision_recall_curve,auc,roc_auc_score,roc_curve,recall_score,classification_report

# Compute and plot confusion matrix
cnf_matrix = confusion_matrix(y_test_undersample,y_predict_undersample)

#Model overall accuracy
print("the Model overall accuracy is :",(cnf_matrix[1,1]+cnf_matrix[0,0])/(cnf_matrix[1,1]+cnf_matrix[1,0]+cnf_matrix[1,0]+cnf_matrix[0,0]))
print()
print("the recall of fraud is :",cnf_matrix[1,1]/(cnf_matrix[1,1]+cnf_matrix[1,0]))
print("the precision of fraud is :",cnf_matrix[1,1]/(cnf_matrix[1,1]+cnf_matrix[0,1]))
print()
print("the recall of normal is :",cnf_matrix[0,0]/(cnf_matrix[0,0]+cnf_matrix[0,1]))
print("the precision of normal is :",cnf_matrix[0,0]/(cnf_matrix[0,0]+cnf_matrix[1,0]))

fig= plt.figure(figsize=(6,3))# to plot the graph
print("TP",cnf_matrix[1,1]) # no of fraud transaction which are predicted fraud
print("TN",cnf_matrix[0,0]) # no.of normal transaction which are predited normal
print("FP",cnf_matrix[0,1]) # no of normal transaction which are predicted fraud
print("FN",cnf_matrix[1,0]) # no of fraud Transaction which are predicted normal
sns.heatmap(cnf_matrix,cmap="coolwarm_r",annot=True,linewidths=0.5)
plt.title("Confusion_matrix")
plt.xlabel("Predicted_class")
plt.ylabel("Real class")
plt.show()

the Model overall accuracy is : 0.9984084880636604

the recall of fraud is : 0.9983818770226537
the precision of fraud is : 0.9973060344827587

the recall of normal is : 0.997393117831074
the precision of normal is : 0.9984342379958246
TP 1851
TN 1913
FP 5
FN 3

#NEXT IS USE THE GLOBAL DATA

# 从sklearn.preprocessing里导入数据标准化模块。
from sklearn.preprocessing import StandardScaler

# 从仍然需要对训练和测试的特征数据进行标准化。
ss = StandardScaler()
X_train = ss.fit_transform(X_train)
X_test = ss.transform(X_test)

# 初始化线性假设的支持向量机分类器LinearSVC。
dt_ = DecisionTreeClassifier(splitter='best')
#进行模型训练
dt_.fit(X_train, y_train)
# 利用训练好的模型对测试样本的数字类别进行预测，预测结果储存在变量y_predict中。
y_predict = dt_.predict(X_test)

# Compute and plot confusion matrix
cnf_matrix = confusion_matrix(y_test,y_predict)

#Model overall accuracy
print("the Model overall accuracy is :",(cnf_matrix[1,1]+cnf_matrix[0,0])/(cnf_matrix[1,1]+cnf_matrix[1,0]+cnf_matrix[1,0]+cnf_matrix[0,0]))
print()
print("the recall of fraud is :",cnf_matrix[1,1]/(cnf_matrix[1,1]+cnf_matrix[1,0]))
print("the precision of fraud is :",cnf_matrix[1,1]/(cnf_matrix[1,1]+cnf_matrix[0,1]))
print()
print("the recall of normal is :",cnf_matrix[0,0]/(cnf_matrix[0,0]+cnf_matrix[0,1]))
print("the precision of normal is :",cnf_matrix[0,0]/(cnf_matrix[0,0]+cnf_matrix[1,0]))

fig= plt.figure(figsize=(6,3))# to plot the graph
print("TP",cnf_matrix[1,1]) # no of fraud transaction which are predicted fraud
print("TN",cnf_matrix[0,0]) # no.of normal transaction which are predited normal
print("FP",cnf_matrix[0,1]) # no of normal transaction which are predicted fraud
print("FN",cnf_matrix[1,0]) # no of fraud Transaction which are predicted normal
sns.heatmap(cnf_matrix,cmap="coolwarm_r",annot=True,linewidths=0.5)
plt.title("Confusion_matrix")
plt.xlabel("Predicted_class")
plt.ylabel("Real class")
plt.show()

the Model overall accuracy is : 0.9989949748743718

the recall of fraud is : 0.997872340425532
the precision of fraud is : 0.997872340425532

the recall of normal is : 0.9993421052631579
the precision of normal is : 0.9993421052631579
TP 1876
TN 6076
FP 4
FN 4

	Organization_Number	Registration_Month	Bransje	Fylke	Kommune	Stiftet	Share_Capital	Organization_Form	Ansatte	Class
0	811108952	8	41	7	704	1988	120000	10	0	1
1	811549452	4	74	1	101	2013	30000	10	0	1
2	811594962	2	43	50	5001	2013	30000	10	0	1
3	811618462	11	41	18	1860	2013	0	2	1	1
4	811678252	10	43	50	5024	2013	30000	10	0	1