# prediction code
X = dataframe.filter(['feature1', 'feature2', 'feature3', 'feature4', 'feature5'])
y = dataframe.filter(['dependent_variable'])

# import sklearn and train,test and split packages
from sklearn.cross_validation import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)

# logistic regression is the prediction algorithm of choice
from sklearn.linear_model import LogistricRegression
from sklearn import metrics
logreg = LogisticRegression()
logreg.fit(X_train, y_train)

# Determine the accuracy of model
from sklearn.metrics import accuracy_score
Logreg.fit(X_train, y_train)
Predictions = logreg.predict(X_test)
accuracy = accuracy_score(y_test, predictions)

# scoring the model
print('Accuracy score: ')
print(accuracy)

# cross validation matrix for accuracy
confusion_matrix = confusion_matrix(y_test, predictions)
print (confusion_matrix)
fig, ax - plot_confusion_matrix(conf_mat=confusion_matrix)
plt.show()
print('#TRUES POSITIVE | FALSE POSITIVE')
print('FALSE NEGATIVE | #TRUE NEGATIVE')