def main():
data_path = '../data/'
nightlights_bins_file = data_path + 'nightlights_bins.csv'
satellite_images_dir = data_path + 'images/'
training_images_dir = data_path + 'train_val/'
report_dir = data_path + 'report/'
report_file = report_dir + 'report.csv'
try:
data_download.get_satellite_images_with_labels(
nightlights_bins_file,
satellite_images_dir,
report_dir,
scale=1,
zoom=17,
imgsize=(400,400)
)
except:
logging.debug("Could not download satellite images. Please set your API keys.")
# To see how nightlights_bins_file was generated, please refer to
# notebooks/01_lights_eda.ipynb
nightlights = pd.read_csv(nightlights_bins_file)
report = pd.read_csv(report_file)
# Initialize train and val sets
nightlights = nightlights.sample(frac=1, random_state=SEED).reset_index(drop=True)
train, val = data_utils.train_val_split(nightlights, train_size=0.9)
train_balanced = data_utils.balance_dataset(train, size=30000)
# Split dataset into training and validation sets
data_utils.train_val_split_images(val, report, training_images_dir, phase='val')
data_utils.train_val_split_images(train_balanced, report, training_images_dir, phase='train')
nightlights = nightlights.sample(
frac=1, random_state=SEED).reset_index(drop=True)
train, val = data_utils.train_val_split(nightlights, train_size=0.9)
print('Size of training set: ', len(train))
print(train['label'].value_counts())
print('\nSize of validation set: ', len(val))
print(val['label'].value_counts())
# ### Upsample Minority Class of Training Set
# In[32]:
train_balanced = data_utils.balance_dataset(train, size=30000)
print('Number of images in training set (balanced): ', len(train_balanced))
train_balanced['label'].value_counts()
# ## Downloading the Google Static Maps (GSM) Images
#
# To download the GSM images, run `src/data_download.py` as follows:
# ```
# cd src
# python data_download.py
# ```
# In[ ]: