from sklearn.model_selection import train_test_split
import torch
import torch.nn as nn
import pandas as pd
import numpy as np
import torch.nn.functional as F
from torch.utils.data import DataLoader, TensorDataset, random_split
from sklearn import preprocessing
import sys

class LogisticRegressionModel(torch.nn.Module):
    def __init__(self, input_dim, output_dim):
        super(LogisticRegressionModel, self).__init__()
        self.linear = nn.Linear(input_dim, output_dim)
        self.sigmoid = nn.Sigmoid()
    def forward(self, x):
        out = self.linear(x)
        return self.sigmoid(out)

results = pd.read_csv('diabetes2.csv')

results.dropna()

data_train, data_valid, data_test = np.split(results.sample(frac=1), [int(.6*len(results)), int(.8*len(results))])
columns_to_train   =  ['Glucose', 'BloodPressure', 'Insulin', 'Age']

x_train = data_train[columns_to_train].astype(np.float32)
y_train = data_train['Outcome'].astype(np.float32)

x_test = data_test[columns_to_train].astype(np.float32)
y_test = data_test['Outcome'].astype(np.float32)

fTrain = torch.from_numpy(x_train.values)
tTrain = torch.from_numpy(y_train.values.reshape(460,1))

fTest= torch.from_numpy(x_test.values)
tTest = torch.from_numpy(y_test.values)

batch_size = int(sys.argv[1]) if len(sys.argv) > 1 else 20
n_iters = 900
num_epochs = int(sys.argv[2]) if len(sys.argv) > 2 else 10
learning_rate = 0.005
input_dim = 4
output_dim = 1

model = LogisticRegressionModel(input_dim, output_dim)

criterion = torch.nn.BCELoss(reduction='mean')
optimizer = torch.optim.SGD(model.parameters(), lr = learning_rate)

for epoch in range(num_epochs):
    print ("Epoch - ",epoch)
    model.train()
    optimizer.zero_grad()
    # Forward pass
    y_pred = model(fTrain)
    # Compute Loss
    loss = criterion(y_pred, tTrain)
    print(loss.item())
    # Backward pass
    loss.backward()
    optimizer.step()


y_pred = model(fTest)

torch.save(model, 'diabetes.pkl')