More experimentation

Signed-off-by: András Schmelczer <andras@schmelczer.dev>

example/.gitignore

@@ -1,2 +1,3 @@
 data
 .ipynb_checkpoints
+tracing_database.json

example/README.md

@@ -0,0 +1,12 @@
+# Train Domain classifier from the [semantic scholar dataset](https://api.semanticscholar.org/corpus)
+
+## Upload the dataset (or a part of it) to shared infrastructure
+
+```sh
+mkdir ss-data && cd ss-data
+wget https://s3-us-west-2.amazonaws.com/ai2-s2-research-public/open-corpus/2022-02-01/manifest.txt
+wget -B https://s3-us-west-2.amazonaws.com/ai2-s2-research-public/open-corpus/2022-02-01/ -i manifest.txt
+cd -
+python3 -m good_ai.open_s3 --secrets s3.ini --push ss-data
+rm -rf ss-data
+```

example/main.py

@@ -1,15 +1,21 @@
 import json
+from random import shuffle
 
+from devtools import debug
 from predict_domain import predict_domain
 
-from good_ai import LargeFile, process_batch
+from good_ai import process_batch
 
 if __name__ == "__main__":
-    with open("data/s2-corpus-1583.json") as f:
+    with open(".cache/ss-data-0/s2-corpus-1583.json") as f:
         raw = json.load(f)
 
-    LargeFile.configure_credentials_from_file("s3.ini")
-
+    shuffle(raw)
     data = {f'{r["title"]} {r["abstract"]}': r["domain"] for r in raw[:5]}
 
-    print(process_batch(predict_domain, ["We have found a new type of chemical."]))
+    results = process_batch(predict_domain, data.keys())
+
+    for predicted, actual in zip(results, data.values()):
+        print(", ".join(actual))
+        debug(predicted)
+        print()

example/predict_domain.py

@@ -45,7 +45,7 @@ def predict_domain(
             )
         )
 
-        if sum(r.probability for r in results) >= cut_off_probability:
+        if sum(r.probability for r in results) >= cut_off_probability * 100:
             break
 
     return results