2021-04-02 18:08:56 +00:00
|
|
|
import ebay_api
|
2021-06-10 19:28:41 +00:00
|
|
|
import json
|
|
|
|
import pdb
|
2021-04-02 18:08:56 +00:00
|
|
|
|
|
|
|
'''
|
|
|
|
file used to compile methods from ebay_api.py for curating training data
|
|
|
|
'''
|
|
|
|
curate = ebay_api.CurateData()
|
|
|
|
raw_data = curate.import_raw()
|
2021-06-10 19:28:41 +00:00
|
|
|
training = curate.to_training(raw_data) # creates raw_df
|
|
|
|
class_training = curate.class_training(training) # creates initial class_training df
|
|
|
|
nvl_training = curate.nvl_training(training) # creates initial nvl_training
|
|
|
|
dropd = curate.drop_nvl_cols(nvl_training) # label mask
|
2021-04-02 18:08:56 +00:00
|
|
|
|
2021-06-10 19:28:41 +00:00
|
|
|
expanded_dfs = curate.expand_nvlclass(class_training, dropd) # pulls values out of lists
|
2021-04-07 22:50:23 +00:00
|
|
|
|
2021-06-10 19:28:41 +00:00
|
|
|
expanded_class = expanded_dfs[0] # TODO still having problems with Unnamed: 0 col
|
|
|
|
expanded_dropd = expanded_dfs[1] # TODO incorrect df. Look at nvl_training func. Specifically "reindex" usage
|
2021-04-07 22:50:23 +00:00
|
|
|
|
2021-06-10 19:28:41 +00:00
|
|
|
download = input('download images?: ')
|
|
|
|
if ('y' or 'Y') in download:
|
|
|
|
with open('temp_pics_source_list.txt') as f:
|
|
|
|
test_list = json.load(f)
|
|
|
|
curate.dl_pictures(test_list)
|
|
|
|
else:
|
|
|
|
pass
|