Python数据分析：糖尿病视网膜病变数据分析

# 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 in 

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 "../input/" directory.
# For example, running this (by clicking run or pressing Shift+Enter) will list the files in the input directory

import os, sys
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import skimage.io
from skimage.transform import resize
from imgaug import augmenters as iaa
from tqdm import tqdm
import PIL
from PIL import Image, ImageOps
import cv2
from sklearn.utils import class_weight, shuffle
from keras.losses import binary_crossentropy
from keras.applications.resnet50 import preprocess_input
import keras.backend as K
import tensorflow as tf
from sklearn.metrics import f1_score, fbeta_score
from keras.utils import Sequence
from keras.utils import to_categorical
from sklearn.model_selection import train_test_split
'''
遇到不懂的问题？Python学习交流群：1136201545
满足你的需求，资料都已经上传群文件，可以自行下载！
'''

WORKERS = 2
CHANNEL = 3

import warnings
warnings.filterwarnings("ignore")
IMG_SIZE = 512
NUM_CLASSES = 5
SEED = 77
TRAIN_NUM = 1000 # use 1000 when you just want to explore new idea, use -1 for full train

df_train = pd.read_csv('F:\\kaggleDataSet\\diabeticRetinopathy\\trainLabels19.csv')
df_test = pd.read_csv('F:\\kaggleDataSet\\diabeticRetinopathy\\testImages19.csv')

x = df_train['id_code']
y = df_train['diagnosis']

x, y = shuffle(x, y, random_state=SEED)

train_x, valid_x, train_y, valid_y = train_test_split(x, y, test_size=0.15,stratify=y, random_state=SEED)
print(train_x.shape, train_y.shape, valid_x.shape, valid_y.shape)
train_y.hist()
valid_y.hist()

'''
遇到不懂的问题？Python学习交流群：1136201545
满足你的需求，资料都已经上传群文件，可以自行下载！
'''
%%time
fig = plt.figure(figsize=(25, 16))
# display 10 images from each class
for class_id in sorted(train_y.unique()):
    for i, (idx, row) in enumerate(df_train.loc[df_train['diagnosis'] == class_id].sample(5, random_state=SEED).iterrows()):
        ax = fig.add_subplot(5, 5, class_id * 5 + i + 1, xticks=[], yticks=[])
        path="F:\\kaggleDataSet\\diabeticRetinopathy\\resized train 19\\"+str(row['id_code'])+".jpg"
        image = cv2.imread(path)
        image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
        image = cv2.resize(image, (IMG_SIZE, IMG_SIZE))
        plt.imshow(image)
        ax.set_title('Label: %d-%d-%s' % (class_id, idx, row['id_code']) )