import numpy as np
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression

from sklearn.preprocessing import StandardScaler

df = pd.read_excel('credit_clients.xls')

data = df.iloc[1:,0:-1]
target = df.iloc[1:,-1]
data_np = np.array(data, dtype=np.int16)
target_np = np.array(target, dtype=np.int16)

scaler = StandardScaler()
data_np = scaler.fit_transform(data_np)

df_train_data, df_test_data, \
df_train_target, df_test_target = \
train_test_split(data_np,target_np, test_size=0.1)

logistic_regression = LogisticRegression()
logistic_regression.fit(df_train_data, df_train_target)

id=6
prediction = logistic_regression.predict(df_test_data[id,:].reshape(1,-1))
print("Model predicted for person {0} value {1}".format(id, prediction))

print("Real value for person \"{0}\" is {1}".format(id, df_test_target[id]))

prediction_probability = logistic_regression.predict_proba(df_test_data[id,:].reshape(1,-1))
print(prediction_probability)

from sklearn.metrics import accuracy_score
acc = accuracy_score(df_test_target, logistic_regression.predict(df_test_data))
print("Model accuracy is {0:0.2f}".format(acc))

from sklearn.metrics import confusion_matrix

conf_matrix = confusion_matrix(df_test_target, logistic_regression.predict(df_test_data))
print(conf_matrix)