Last active
August 24, 2022 15:52
-
-
Save aniruddha27/ac7018bf3d8047abb52648b28a5ffee8 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import pandas as pd | |
import os | |
import shutil | |
from sklearn.model_selection import train_test_split | |
# Home directory | |
home_path = r'C:/Users/Dell/Desktop/Analytics Vidhya/ImageDataGenerator/emergency_vs_non-emergency_dataset/emergency_vs_non-emergency_dataset' | |
# Create train and validation directories | |
train_path = os.path.join(home_path,'train') | |
os.mkdir(train_path) | |
val_path = os.path.join(home_path,'valid') | |
os.mkdir(val_path) | |
# Create sub-directories | |
emergency_train_path = os.path.join(home_path + r'/train','emergency') | |
os.mkdir(emergency_train_path) | |
non_emergency_train_path = os.path.join(home_path + r'/train','non_emergency') | |
os.mkdir(non_emergency_train_path) | |
emergency_val_path = os.path.join(home_path + r'/valid','emergency') | |
os.mkdir(emergency_val_path) | |
non_emergency_val_path = os.path.join(home_path + r'/valid','non_emergency') | |
os.mkdir(non_emergency_val_path) | |
# Original df | |
df = pd.read_csv(home_path + r'/emergency_train.csv') | |
# Images and Labels | |
X = df.loc[:,'image_names'] | |
y = df.loc[:,'emergency_or_not'] | |
# Train-Test splitfor train and validation images | |
train_x, val_x, train_y, val_y = train_test_split(X, y, test_size = 0.1, random_state = 27, stratify=y) | |
# Train df | |
df_train = pd.DataFrame(columns=['image_names','emergency_or_not']) | |
df_train['image_names'] = train_x | |
df_train['emergency_or_not'] = train_y | |
# Validation df | |
df_valid= pd.DataFrame(columns=['image_names','emergency_or_not']) | |
df_valid['image_names'] = val_x | |
df_valid['emergency_or_not'] = val_y | |
# Reset index | |
df_train.reset_index(drop=True, inplace=True) | |
df_valid.reset_index(drop=True, inplace=True) | |
# Save train images | |
for i in range(len(df_train)): | |
image = df_train.loc[i,'image_names'] | |
if df_train.loc[i,'emergency_or_not'] == 0: | |
shutil.copy(home_path + r'/images/' + image, non_emergency_train) | |
else: | |
shutil.copy(home_path + r'/images/' + image, emergency_train) | |
# Save validation images | |
for i in range(len(df_valid)): | |
image = df_valid.loc[i,'image_names'] | |
if df_valid.loc[i,'emergency_or_not'] == 0: | |
shutil.copy(home_path + r'/images/' + image, non_emergency_val) | |
else: | |
shutil.copy(home_path + r'/images/' + image, emergency_val) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment