Jovian
Sign In
Learn practical skills, build real-world projects, and advance your career
4 years ago
!kaggle datasets download -d nih-chest-xrays/data
Traceback (most recent call last): File "/opt/conda/bin/kaggle", line 5, in <module> from kaggle.cli import main File "/opt/conda/lib/python3.7/site-packages/kaggle/__init__.py", line 23, in <module> api.authenticate() File "/opt/conda/lib/python3.7/site-packages/kaggle/api/kaggle_api_extended.py", line 149, in authenticate self.config_file, self.config_dir)) OSError: Could not find kaggle.json. Make sure it's located in /root/.kaggle. Or use the environment method. 
# This Python 3 environment comes with many helpful analytics libraries installed
# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python
# For example, here's several helpful packages to load

import numpy as np # linear algebra
import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)

# Input data files are available in the read-only "../input/" directory
# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory

# import os
# for dirname, _, filenames in os.walk('/kaggle/input'):
#     for filename in filenames:
#         print(os.path.join(dirname, filename))

# You can write up to 5GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using "Save & Run All" 
# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session
import os
import torch
import os
from glob import glob
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 torchvision.transforms as transforms
import matplotlib.pyplot as plt
from tqdm.notebook import tqdm
import torchvision.transforms as transforms
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/data/"
train = open(DATA_DIR + "train_val_list.txt", "r")
train = train.read().split("\n")

test = open(DATA_DIR + "test_list.txt", "r")
test = test.read().split("\n")

data = pd.read_csv('../input/data/Data_Entry_2017.csv')
data = data.iloc[:, [0, 1]]

trainval = data[data["Image Index"].isin(train)][["Image Index","Finding Labels"]]
testval = data[data["Image Index"].isin(test)][["Image Index","Finding Labels"]]
trainval.insert(0,"Type", "TRAIN")
testval.insert(0,"Type", "TEST")
datalist = pd.concat([trainval,testval], axis=0, ignore_index=True)
datalist

all_xray_df = datalist
all_image_paths = {os.path.basename(x): x for x in 
                   glob(os.path.join('..', 'input', 'data', 'images*', '*', '*.png'))}
print('Scans found:', len(all_image_paths), ', Total Headers', all_xray_df.shape[0])
all_xray_df['path'] = all_xray_df['Image Index'].map(all_image_paths.get)
Scans found: 112120 , Total Headers 112120 
data = all_xray_df
data