import os
import torch
import pandas as pd
import numpy as np
from torch.utils.data import Dataset, random_split, DataLoader
from PIL import Image
import torchvision.models as models
import matplotlib.pyplot as plt
from tqdm.notebook import tqdm
import torchvision.transforms as T
from sklearn.metrics import f1_score
import torch.nn.functional as F
import torch.nn as nn
from torchvision.utils import make_grid
%matplotlib inline

DATA_DIR = '../input/jovian-pytorch-z2g/Human protein atlas'

TRAIN_DIR = DATA_DIR + '/train'                           
TEST_DIR = DATA_DIR + '/test'                             

TRAIN_CSV = DATA_DIR + '/train.csv'                       
TEST_CSV = '../input/jovian-pytorch-z2g/submission.csv' 
data_df = pd.read_csv(TRAIN_CSV)
print(data_df.head())
labels = {
    0: 'Mitochondria',
    1: 'Nuclear bodies',
    2: 'Nucleoli',
    3: 'Golgi apparatus',
    4: 'Nucleoplasm',
    5: 'Nucleoli fibrillar center',
    6: 'Cytosol',
    7: 'Plasma membrane',
    8: 'Centrosome',
    9: 'Nuclear speckles'
}

def encode_label(label):
    target = torch.zeros(10)
    for l in str(label).split(' '):
        target[int(l)] = 1.
    return target

def decode_target(target, text_labels=False, threshold=0.5):
    result = []
    for i, x in enumerate(target):
        if (x >= threshold):
            if text_labels:
                result.append(labels[i] + "(" + str(i) + ")")
            else:
                result.append(str(i))
    return ' '.join(result)
def show_sample(img, target, invert=True):
    if invert:
        plt.imshow(1 - img.permute((1, 2, 0)))
    else:
        plt.imshow(img.permute(1, 2, 0))
    print('Labels:', decode_target(target, text_labels=True))
    
def show_batch(dl, invert=True):
    for images, labels in dl:
        fig, ax = plt.subplots(figsize=(16, 8))
        ax.set_xticks([]); ax.set_yticks([])
        data = 1-images if invert else images
        ax.imshow(make_grid(data, nrow=16).permute(1, 2, 0))
        break