Update app.py

app.py

@@ -1,121 +1,124 @@
-from flask import Flask, render_template, request, redirect, url_for
-from joblib import load
-import pandas as pd
-import re
-from customFunctions import *
-import json
-import datetime
-
-pd.set_option('display.max_colwidth', 1000)
-
-PIPELINES = [
-    {
-        'id': 1,
-        'name': 'Baseline',
-        'pipeline': load("pipeline_ex1_s1.joblib")
-    },
-    {
-        'id': 2,
-        'name': 'Trained on a FeedForward NN',
-        'pipeline': load("pipeline_ex1_s2.joblib")
-    },
-    {
-        'id': 3,
-        'name': 'Trained on a CRF',
-        'pipeline': load("pipeline_ex1_s3.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")
-    #},
-    
-]
-
-pipeline_metadata = [{'id': p['id'], 'name': p['name']} for p in PIPELINES]
-
-def get_pipeline_by_id(pipelines, pipeline_id):
-    return next((p['pipeline'] for p in pipelines if p['id'] == pipeline_id), None)
-
-def get_name_by_id(pipelines, pipeline_id):
-    return next((p['name'] for p in pipelines if p['id'] == pipeline_id), None)
-
-
-
-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
-
-def log_interaction(user_input, model_name, predictions):
-    log_entry = {
-        "timestamp": datetime.datetime.utcnow().isoformat(),
-        "user_input": user_input,
-        "model": model_name,
-        "predictions": predictions
-    }
-    with open(LOG_FILE, "a") as f:
-        f.write(json.dumps(log_entry) + "\n")
-
-
-app = Flask(__name__)
-
-
-@app.route('/')
-def index():
-    return render_template('index.html', pipelines= pipeline_metadata)
-
-
-@app.route('/', methods=['POST'])
-def get_data():
-    if request.method == 'POST':
-
-        text = request.form['search']
-        tokens = re.findall(r"\w+|[^\w\s]", text)
-        tokens_fomatted = pd.Series([pd.Series(tokens)])
-
-        pipeline_id = int(request.form['pipeline_select'])
-        pipeline = get_pipeline_by_id(PIPELINES, pipeline_id)
-        name = get_name_by_id(PIPELINES, pipeline_id)
-        
-        labels = requestResults(tokens_fomatted, pipeline)
-        results = dict(zip(tokens, labels))
-
-        log_interaction(text, name, results)
-
-        return render_template('index.html', results=results, name=name, pipelines= pipeline_metadata)
-
-
-if __name__ == '__main__':
-    app.run(host="0.0.0.0", port=7860)
-
-#if __name__ == '__main__':
-#app.run(host="0.0.0.0", port=7860)
+from flask import Flask, render_template, request, redirect, url_for
+from joblib import load
+import pandas as pd
+import re
+from customFunctions import *
+import json
+import datetime
+
+pd.set_option('display.max_colwidth', 1000)
+
+PIPELINES = [
+    {
+        'id': 1,
+        'name': 'Baseline',
+        'pipeline': load("pipeline_ex1_s1.joblib")
+    },
+    {
+        'id': 2,
+        'name': 'Trained on a FeedForward NN',
+        'pipeline': load("pipeline_ex1_s2.joblib")
+    },
+    {
+        'id': 3,
+        'name': 'Trained on a CRF',
+        'pipeline': load("pipeline_ex1_s3.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")
+    #},
+    
+]
+
+pipeline_metadata = [{'id': p['id'], 'name': p['name']} for p in PIPELINES]
+
+def get_pipeline_by_id(pipelines, pipeline_id):
+    return next((p['pipeline'] for p in pipelines if p['id'] == pipeline_id), None)
+
+def get_name_by_id(pipelines, pipeline_id):
+    return next((p['name'] for p in pipelines if p['id'] == pipeline_id), None)
+
+
+
+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
+
+def log_interaction(user_input, model_name, predictions):
+    log_entry = {
+        "timestamp": datetime.datetime.utcnow().isoformat(),
+        "user_input": user_input,
+        "model": model_name,
+        "predictions": predictions
+    }
+    with open(LOG_FILE, "a") as f:
+        f.write(json.dumps(log_entry) + "\n")
+
+
+app = Flask(__name__)
+
+
+@app.route('/')
+def index():
+    return render_template('index.html', pipelines= pipeline_metadata)
+
+
+@app.route('/', methods=['POST'])
+def get_data():
+    if request.method == 'POST':
+
+        text = request.form['search']
+        tokens = re.findall(r"\w+|[^\w\s]", text)
+        tokens_fomatted = pd.Series([pd.Series(tokens)])
+
+        pipeline_id = int(request.form['pipeline_select'])
+        pipeline = get_pipeline_by_id(PIPELINES, pipeline_id)
+        name = get_name_by_id(PIPELINES, pipeline_id)
+        
+        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}")
+
+
+        return render_template('index.html', results=results, name=name, pipelines= pipeline_metadata)
+
+
+if __name__ == '__main__':
+    app.run(host="0.0.0.0", port=7860)
+
+#if __name__ == '__main__':
+#app.run(host="0.0.0.0", port=7860)