# Imports
import torch
import jovian
import torchvision
import torch.nn as nn
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import torch.nn.functional as F
from torchvision.datasets.utils import download_url
from torch.utils.data import DataLoader, TensorDataset, random_split

# Hyperparameters
# Other constants
DATASET_URL = "housing.csv"
DATA_FILENAME = "housing.csv"
TARGET_COLUMN = 'ocean_proximity'

# Download the data
dataframe_raw = pd.read_csv(DATASET_URL)
dataframe_raw.head()

def customize_dataset(dataframe_raw):
    dataframe = dataframe_raw.copy(deep=True)
    # drop some columns
    dataframe = dataframe.drop(['longitude', 'latitude'], axis=1)
    #for col in ['housing_median_age', 'total_rooms', 'total_bedrooms', 'population', 
    #            'households', 'median_income' ,'median_house_value']:
    #    # normalizing incoming data
    #    dataframe[col] = (dataframe[col] - min(dataframe[col])) / (max(dataframe[col]) - min(dataframe[col]))
    
    # dropping any row that contains at least on missing value
    # if you dont do that, loss function will be returning nan
    dataframe = dataframe.dropna(axis=0)  
    
    return dataframe