predict

app.py

@@ -23,10 +23,23 @@ tokenizer = AutoTokenizer.from_pretrained("rabiaqayyum/autotrain-mental-health-a
 model = pickle.load(open("model.pkl", "rb"))
 
 def classify_text(inp):
-    input_ids = tokenizer.encode(inp, return_tensors='pt')
-    output = model.predict(input_ids)
-    return output.logits.argmax().item()
-
+    # input_ids = tokenizer.encode(inp, return_tensors='pt')
+    # output = model.predict(input_ids)
+    # return output.logits.argmax().item()
+    vectorizer = TfidfVectorizer()
+    X = vectorizer.fit_transform(inp)
+    return model.predict(X)
+
+    
+
+# # encode the input text
+#     encoded_input = tokenizer(text, return_tensors='pt')
+#     # get the prediction
+#     output = model(**encoded_input)
+#     # get the label
+#     label = output[0].argmax().item()
+#     # return the label
+#     return label
 iface = gr.Interface(fn=classify_text, inputs="text", outputs="label",
                         interpretation="default", examples=[
                             ["I am feeling depressed"],

model.ipynb

@@ -181,7 +181,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 10,
    "id": "c5dde0e4",
    "metadata": {},
    "outputs": [
@@ -189,7 +189,8 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Accuracy: 0.06666666666666667\n"
+      "(148, 252)\n",
+      "Accuracy: 0.0\n"
      ]
     }
    ],
@@ -212,6 +213,7 @@
     "X = vectorizer.fit_transform(questions)\n",
     "y = responses\n",
     "\n",
+    "\n",
     "# Step 2: Split data into training and testing sets\n",
     "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)\n",
     "\n",