Edit how pipelines are found (#5)

- Edit how pipelines are found (dfce2de6926fceaddb38345ad47ca56277da2892)


Co-authored-by: H Wilks <[email protected]>

app.py

@@ -6,10 +6,12 @@ from customFunctions2 import *
 import json
 import datetime
 import numpy as np
+from huggingface_hub import hf_hub_download
+import torch
+
 
 pd.set_option('display.max_colwidth', 1000)
 
-import torch
 
 # Patch torch.load to always load on CPU
 original_torch_load = torch.load
@@ -18,47 +20,51 @@ def cpu_load(*args, **kwargs):
 
 torch.load = cpu_load
 
+def load_pipeline_from_hub(filename):
+    repo_id = 'hw01558/nlp-coursework-pipelines'
+    local_path = hf_hub_download(repo_id=repo_id, filename=filename)
+    return load(local_path)
 
 PIPELINES = [
     {
         'id': 1,
         'name': 'Baseline',
-        'pipeline': load("pipelines/pipeline_ex1_s1.joblib")
+        'pipeline': load_pipeline_from_hub("pipeline_ex1_s1.joblib")
     },
     {
         'id': 2,
         'name': 'Trained on a FeedForward NN',
-        'pipeline': load("pipelines/pipeline_ex1_s2.joblib")
+        'pipeline': load_pipeline_from_hub("pipeline_ex1_s2.joblib")
     },
     {
         'id': 3,
         'name': 'Trained on a CRF',
-        'pipeline': load("pipelines/pipeline_ex1_s3.joblib")
+        'pipeline': load_pipeline_from_hub("pipeline_ex1_s2.joblib")
     },
     {
         'id': 4,
         'name': 'Trained on a small dataset',
-        'pipeline': load("pipelines/pipeline_ex2_s3.joblib")
+        'pipeline': load_pipeline_from_hub("pipeline_ex2_s3.joblib")
     },
     {
         'id': 5,
         'name': 'Trained on a large dataset',
-        'pipeline': load("pipelines/pipeline_ex2_s2.joblib")
+        'pipeline': load_pipeline_from_hub("pipeline_ex2_s2.joblib")
     },
     {
         'id': 6,
         'name': 'Embedded using TFIDF',
-        'pipeline': load("pipelines/pipeline_ex3_s2.joblib")
+        'pipeline': load_pipeline_from_hub("pipeline_ex3_s2.joblib")
     },
     {
         'id': 7,
         'name': 'Embedded using GloVe',
-        'pipeline': load("pipelines/pipeline_ex3_s3.joblib")
+        'pipeline': load_pipeline_from_hub("pipeline_ex3_s3.joblib")
     },
     {
          'id': 8,
          'name': 'Embedded using Bio2Vec',
-         'pipeline': load("pipelines/pipeline_ex3_s4.joblib")
+        'pipeline': load_pipeline_from_hub("pipeline_ex3_s4.joblib")
     },
     
 ]
@@ -131,3 +137,5 @@ def get_data():
 if __name__ == '__main__':
     app.run(host="0.0.0.0", port=7860)
 
+#if __name__ == '__main__':
+#app.run(host="0.0.0.0", port=7860)