import pandas as pd
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import train_test_split
from sklearn.metrics import confusion_matrix
from sklearn.metrics import accuracy_score
# import warnings filter
from warnings import simplefilter

# ignore all future warnings
simplefilter(action='ignore', category=FutureWarning)

dtypes = {'order_id': int, 'store_id': int, 'name': object, 'email': object, 'telephone': object,
          'payment_postcode': object, 'payment_country_id': int, 'payment_code': object, 'total': float, 'ip': object,
          'forwarded_ip': object, 'blacklisted': bool}

orderData = pd.read_csv('order-data.csv', low_memory=False, keep_default_na=False, dtype=dtypes)

# print(orderData.head())
# print(orderData.describe())
# print(orderData.corr())

features = orderData[['name', 'email', 'total']]
target = orderData.blacklisted

# 30% data will go to test data set
feature_train, feature_test, target_train, target_test = train_test_split(features, target, test_size=0.3)

model = LogisticRegression()
model.fit = model.fit(feature_train, target_train)
predictions = model.fit.predict(feature_test)

print(confusion_matrix(target_test, predictions))
print(accuracy_score(target_test, predictions))