Add new pipelines and adjust labels (#3)

- Add new pipelines and adjust labels (1fd311db24e931dfd0c020ed6cd7adaa22f764bd)


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

app.py

@@ -2,48 +2,64 @@ from flask import Flask, render_template, request, redirect, url_for
 from joblib import load
 import pandas as pd
 import re
-from customFunctions import *
+from customFunctions2 import *
 import json
 import datetime
+import numpy as np
 
 pd.set_option('display.max_colwidth', 1000)
 
+import torch
+
+# Patch torch.load to always load on CPU
+original_torch_load = torch.load
+def cpu_load(*args, **kwargs):
+    return original_torch_load(*args, map_location=torch.device('cpu'), **kwargs)
+
+torch.load = cpu_load
+
+
 PIPELINES = [
     {
         'id': 1,
         'name': 'Baseline',
-        'pipeline': load("pipeline_ex1_s1.joblib")
+        'pipeline': load("pipelines/pipeline_ex1_s1.joblib")
     },
     {
         'id': 2,
         'name': 'Trained on a FeedForward NN',
-        'pipeline': load("pipeline_ex1_s2.joblib")
+        'pipeline': load("pipelines/pipeline_ex1_s2.joblib")
     },
     {
         'id': 3,
         'name': 'Trained on a CRF',
-        'pipeline': load("pipeline_ex1_s3.joblib")
+        'pipeline': load("pipelines/pipeline_ex1_s3.joblib")
+    },
+    {
+        'id': 4,
+        'name': 'Trained on a small dataset',
+        'pipeline': load("pipelines/pipeline_ex2_s3.joblib")
+    },
+    {
+        'id': 5,
+        'name': 'Trained on a large dataset',
+        'pipeline': load("pipelines/pipeline_ex2_s2.joblib")
+    },
+    {
+        'id': 6,
+        'name': 'Embedded using TFIDF',
+        'pipeline': load("pipelines/pipeline_ex3_s2.joblib")
+    },
+    {
+        'id': 7,
+        'name': 'Embedded using GloVe',
+        'pipeline': load("pipelines/pipeline_ex3_s3.joblib")
+    },
+    {
+         'id': 8,
+         'name': 'Embedded using Bio2Vec',
+         'pipeline': load("pipelines/pipeline_ex3_s4.joblib")
     },
-    #{
-     #   'id': 4,
-      #  'name': 'Trained on a small dataset',
-       # 'pipeline': load("pipeline_ex2_s1.joblib")
-    #},
-    #{
-     #   'id': 5,
-      #  'name': 'Trained on a large dataset',
-       # 'pipeline': load("pipeline_ex2_s2.joblib")
-    #},
-    #{
-     #   'id': 6,
-      #  'name': 'Embedded using TFIDF',
-       # 'pipeline': load("pipeline_ex3_s1.joblib")
-    #},
-    #{
-     #   'id': 7,
-      #  'name': 'Embedded using ?',
-       # 'pipeline': load("pipeline_ex3_s2.joblib")
-    #},
     
 ]
 
@@ -59,30 +75,29 @@ def get_name_by_id(pipelines, pipeline_id):
 
 def requestResults(text, pipeline):
     labels = pipeline.predict(text)
-    print(labels.ndim)
-    if labels.ndim != 1:
-        flattened_predictions = []
-        for sentence in labels:
-            for tag in sentence:
-                flattened_predictions.append(tag)
-        labels = flattened_predictions
-    print(labels)
-    labels = [int(label) for label in labels]
-    tag_encoder = LabelEncoder()
-    tag_encoder.fit(['B-AC', 'O', 'B-LF', 'I-LF'])
-    decoded_labels = tag_encoder.inverse_transform(labels)
-    return decoded_labels
-
-LOG_FILE = "usage_log.jsonl"  # Each line is a JSON object
+    if isinstance(labels, np.ndarray):
+        labels = labels.tolist()
+    return labels[0]
 
-def log_interaction(user_input, model_name, predictions):
-    print("====== Interaction Log ======")
-    print("Timestamp:", datetime.datetime.utcnow().isoformat())
-    print("Model:", model_name)
-    print("Input:", user_input)
-    print("Predictions:", predictions)
-    print("=============================")
+import os
+
+LOG_FILE = "/tmp/usage_log.jsonl"  # Use temporary file path for Hugging Face Spaces
 
+def log_interaction(user_input, model_name, predictions):
+    log_entry = {
+        "timestamp": datetime.datetime.utcnow().isoformat(),
+        "model": model_name,
+        "user_input": user_input,
+        "predictions": predictions
+    }
+
+    try:
+        os.makedirs(os.path.dirname(LOG_FILE), exist_ok=True)  # Ensure the directory exists
+        with open(LOG_FILE, "a") as log_file:
+            log_file.write(json.dumps(log_entry) + "\n")
+    except Exception as e:
+        print(f"Error writing to log: {e}")
+        # You could also return a response with the error, or raise an error to stop the process
 
 
 app = Flask(__name__)
@@ -108,10 +123,7 @@ def get_data():
         labels = requestResults(tokens_fomatted, pipeline)
         results = dict(zip(tokens, labels))
 
-        print(f"[INFO] Model: {name}")
-        print(f"[INFO] Input: {text}")
-        print(f"[INFO] Output: {results}")
-
+        log_interaction(text, name, results)
 
         return render_template('index.html', results=results, name=name, pipelines= pipeline_metadata)
 
@@ -119,5 +131,3 @@ 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)