import torch
import sys
import torch.nn.functional as F
from torch import nn
from torch.autograd import Variable
import torchvision.transforms as transforms
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import MinMaxScaler
from sklearn.metrics import accuracy_score
import numpy as np
import pandas as pd
from sacred import Experiment
from sacred.observers import FileStorageObserver
np.set_printoptions(suppress=False)

# ex = Experiment("stroke-pytorch", interactive=True) 
# ex.observers.append(FileStorageObserver('ium_s434766O_files'))
# ex.observers.append(MongoObserver(url='mongodb://mongo_user:mongo_password_IUM_2021@localhost:27017',
#                                   db_name='sacred'))
class LogisticRegressionModel(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)

# @ex.main
# def my_main(_log):
data_train = pd.read_csv("data_train.csv")
data_test  = pd.read_csv("data_test.csv")
data_val   = pd.read_csv("data_val.csv")
FEATURES   =  ['age','hypertension','heart_disease','ever_married', 'avg_glucose_level', 'bmi']

x_train = data_train[FEATURES].astype(np.float32)
y_train = data_train['stroke'].astype(np.float32)

x_test = data_test[FEATURES].astype(np.float32)
y_test = data_test['stroke'].astype(np.float32)

fTrain = torch.from_numpy(x_train.values)
tTrain = torch.from_numpy(y_train.values.reshape(2945,1))

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 16
num_epochs = int(sys.argv[2]) if len(sys.argv) > 2 else 5
learning_rate = 0.001
input_dim = 6
output_dim = 1
info_params = "Batch size = " + str(batch_size) + " Epochs = " + str(num_epochs)
# _log.info(info_params)
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()
info_loss = "Last loss = " + str(loss.item())
    # _log.info(info_loss)
y_pred = model(fTest)
print("predicted Y value: ", y_pred.data)

torch.save(model.state_dict(), 'stroke.pth')

# ex.run()