import pandas as pd
import sklearn as sk
import numpy as np
from sklearn.linear_model import LogisticRegression
from sklearn.neural_network import MLPClassifier
from sklearn.tree import DecisionTreeClassifier
from sklearn.neighbors import KNeighborsClassifier
from sklearn.naive_bayes import GaussianNB
from sklearn.model_selection import train_test_split
from sklearn import svm, preprocessing
from sklearn.metrics import confusion_matrix, accuracy_score, precision_score, recall_score
import pickle
from joblib import dump

# ---------------------------------------------------------------------------------------------------------------
#  This file is used to cross validate against the train.txt dataset itself, and generate model as model.joblib
# ---------------------------------------------------------------------------------------------------------------

df = pd.read_csv('train.txt', sep=" ", header=None)
df = df.drop(df.columns[0], axis=1)
df.columns = ["v1","v2","v3","v4","v5","v6","v7","v8","v9","v10", "target"]

X = df.drop(['target'],1)
y = df['target']

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.1)
X_train = preprocessing.scale(X_train)
X_test = preprocessing.scale(X_test)

print ( "Null accuracy: ", max( y_test.mean(), 1 - y_test.mean() ))

model = MLPClassifier(solver='lbfgs',shuffle=True, hidden_layer_sizes=(500), random_state=1)

model.fit(X_train, y_train)

y_pred = model.predict(X_test)

print ( "Confusion Matrix:\n" , confusion_matrix(y_test, y_pred) )
print("Accuracy:",accuracy_score(y_test, y_pred))
print("Precision:",precision_score(y_test, y_pred))
print("Recall:",recall_score(y_test, y_pred))

s = pickle.dumps(model)
dump(model, 'model.joblib')