File tree Expand file tree Collapse file tree 2 files changed +16
-14
lines changed Expand file tree Collapse file tree 2 files changed +16
-14
lines changed Original file line number Diff line number Diff line change @@ -26,17 +26,18 @@ import webbrowser
2626import json
2727from mostlyai import qa
2828
29- # fetch original + synthetic data (in this case a 30% perturbation of the training)
30- repo_url = ' https://github.com/mostly-ai/paper-fidelity-accuracy/raw/refs/heads/main/data/'
31- synthetic_df = pd.read_csv(repo_url + ' online-shoppers_flip30.csv.gz' )
32- training_df = pd.read_csv(repo_url + ' online-shoppers_trn.csv.gz' )
33- holdout_df = pd.read_csv(repo_url + ' online-shoppers_val.csv.gz' )
34-
35- # runs for ~60secs
29+ # fetch original + synthetic data
30+ base_url = ' https://github.com/mostly-ai/mostlyai-qa/raw/refs/heads/main/examples/quick-start'
31+ syn = pd.read_csv(f ' { base_url} /census2k-syn_mostly.csv.gz ' )
32+ # syn = pd.read_csv(f'{base_url}/census2k-syn_flip30.csv.gz') # a 30% perturbation of trn
33+ trn = pd.read_csv(f ' { base_url} /census2k-trn.csv.gz ' )
34+ hol = pd.read_csv(f ' { base_url} /census2k-hol.csv.gz ' )
35+
36+ # runs for ~30secs
3637report_path, metrics = qa.report(
37- syn_tgt_data = synthetic_df ,
38- trn_tgt_data = training_df ,
39- hol_tgt_data = holdout_df ,
38+ syn_tgt_data = syn ,
39+ trn_tgt_data = trn ,
40+ hol_tgt_data = hol ,
4041)
4142
4243# pretty print metrics
Original file line number Diff line number Diff line change 2121 " from mostlyai import qa\n " ,
2222 " \n " ,
2323 " # fetch original + synthetic data\n " ,
24- " syn = pd.read_csv('quick-start/census2k-syn_mostly.csv.gz')\n " ,
25- " # syn = pd.read_csv('quick-start/census2k-syn_flip30.csv.gz') # a 30% perturbation of trn\n " ,
26- " trn = pd.read_csv('quick-start/census2k-trn.csv.gz')\n " ,
27- " hol = pd.read_csv('quick-start/census2k-hol.csv.gz')\n " ,
24+ " base_url = 'https://github.com/mostly-ai/mostlyai-qa/raw/refs/heads/main/examples/quick-start'\n " ,
25+ " syn = pd.read_csv(f'{base_url}/census2k-syn_mostly.csv.gz')\n " ,
26+ " # syn = pd.read_csv(f'{base_url}/census2k-syn_flip30.csv.gz') # a 30% perturbation of trn\n " ,
27+ " trn = pd.read_csv(f'{base_url}/census2k-trn.csv.gz')\n " ,
28+ " hol = pd.read_csv(f'{base_url}/census2k-hol.csv.gz')\n " ,
2829 " \n " ,
2930 " # runs for ~30secs\n " ,
3031 " report_path, metrics = qa.report(\n " ,
You can’t perform that action at this time.
0 commit comments