default to previous build

app.py

@@ -1,197 +1,28 @@
-# import gradio as gr
-
-# def greet(name):
-#     return "Hello " + name + "!!"
-
-# iface = gr.Interface(fn=greet, inputs="text", outputs="text")
-# iface.launch()
-# model = AutoModelForSequenceClassification.from_pretrained("tabibu-ai/mental-health-chatbot")
-
-# write a gradio interface for tabibu-ai/mental-health-chatbot in huggingfacehub
-
-# Path: app.py
-
-
-# -----------------------------------
-# import pickle
-
-# import numpy as np
-# import gradio as gr
-
-# # install transformers and torch in requirements.txt
-
-# from transformers import AutoTokenizer, AutoModelForSequenceClassification
-# from sklearn.feature_extraction.text import TfidfVectorizer
-
-
-# # tokenizer = AutoTokenizer.from_pretrained("tabibu-ai/mental-health-chatbot")
-
-# # tokenizer = AutoTokenizer.from_pretrained("rabiaqayyum/autotrain-mental-health-analysis-752423172")
-# model = pickle.load(open("model.pkl", "rb"))
-# vectorizer = pickle.load(open("vectorizer.pkl", "rb"))
-
-
-# def classify_text(inp):
-#     # 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)
-#     # reshape the input to 2D
-#     # convert the input to a numpy array
-#     # return model.predict( np.array(inp).reshape(1, -1) )
-#     # dtype='numeric' is not compatible with arrays of bytes/strings.Convert your data to numeric values explicitly instead.
-
-#     # Convert inp to numeric values explicitly instead
-#     new_question_vector = vectorizer.transform([inp])
-#     prediction = model.predict(new_question_vector)
-#     # convert the prediction from a numpy array to a string
-#     return str(prediction[0])
-
-# # # 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"],
-#                             ["I am feeling anxious"],
-#                             ["I am feeling stressed"],
-#                             ["I am feeling sad"],
-#                         ])
-# iface.launch()
-
-# -----------------------------------
-
-import nltk
-nltk.download('punkt')
+import pickle
 
-import nltk
-from nltk.stem.lancaster import LancasterStemmer
 import numpy as np
-import tflearn
-import tensorflow
-import random
-import json
-import pandas as pd
-import pickle
 import gradio as gr
 
-stemmer = LancasterStemmer()
-
-with open("intents.json") as file:
-    data = json.load(file)
-
-with open("data.pickle", "rb") as f:
-  words, labels, training, output = pickle.load(f)
-
-net = tflearn.input_data(shape=[None, len(training[0])])
-net = tflearn.fully_connected(net, 8)
-net = tflearn.fully_connected(net, 8)
-net = tflearn.fully_connected(net, len(output[0]), activation="softmax")
-net = tflearn.regression(net)
-
-model = tflearn.DNN(net)
-model.load("MentalHealthChatBotmodel.tflearn")
-# print('model loaded successfully')
-
-
-def bag_of_words(s, words):
-    bag = [0 for _ in range(len(words))]
-
-    s_words = nltk.word_tokenize(s)
-    s_words = [stemmer.stem(word.lower()) for word in s_words]
-
-    for se in s_words:
-        for i, w in enumerate(words):
-            if w == se:
-                bag[i] = 1
-            
-    return np.array(bag)
-
-
-def chat(message, history):
-    history = history or []
-    message = message.lower()
-    results = model.predict([bag_of_words(message, words)])
-    results_index = np.argmax(results)
-    tag = labels[results_index]
+# install transformers and torch in requirements.txt
 
-    for tg in data["intents"]:
-      if tg['tag'] == tag:
-        responses = tg['responses']
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+from sklearn.feature_extraction.text import TfidfVectorizer
 
-        # print(random.choice(responses))
-        response = random.choice(responses)
-  
-    history.append((message, response))
-    return history, history
+model = pickle.load(open("model.pkl", "rb"))
+vectorizer = pickle.load(open("vectorizer.pkl", "rb"))
 
-chatbot = gr.Chatbot(label="Chat")
-css = """
 
-.gr-button-primary {
-    z-index: 14;
-    height: 43px;
-    width: 130px;
-    left: 0px;
-    top: 0px;
-    padding: 0px;
-    cursor: pointer !important; 
+def classify_text(inp):
     
-    border: none !important;
-    text-align: center !important;
-    font-family: Poppins !important;
-    font-size: 14px !important;
-    font-weight: 500 !important;
-    color: rgb(255, 255, 255) !important;
-    line-height: 1 !important;
-    border-radius: 12px !important;
-    transition: box-shadow 200ms ease 0s, background 200ms ease 0s !important;
-    box-shadow: none !important;
-}
-.gr-button-primary:hover{
-    z-index: 14;
-    height: 43px;
-    width: 130px;
-    left: 0px;
-    top: 0px;
-    padding: 0px;
-    cursor: pointer !important;
-    background: none rgb(37, 56, 133) !important;
-    border: none !important;
-    text-align: center !important;
-    font-family: Poppins !important;
-    font-size: 14px !important;
-    font-weight: 500 !important;
-    color: rgb(255, 255, 255) !important;
-    line-height: 1 !important;
-    border-radius: 12px !important;
-    transition: box-shadow 200ms ease 0s, background 200ms ease 0s !important;
-    box-shadow: rgb(0 0 0 / 23%) 0px 1px 7px 0px !important;
-}
-.hover\:bg-orange-50:hover {
-    --tw-bg-opacity: 1 !important;
-    background-color: rgb(229,225,255) !important;
-}
-div[data-testid="user"] {
-  background-color: #253885 !important;
-}
-.h-\[40vh\]{
-height: 70vh !important;
-}
-"""
-demo = gr.Interface(
-    chat,
-    [gr.Textbox(lines=1, label="Message"), "state"],
-    [chatbot, "state"],
-    allow_flagging="never",
-    title="Mental Health Bot | Data Science Dojo",
-    css=css
-)
-if __name__ == "__main__":
-    demo.launch()
+    new_question_vector = vectorizer.transform([inp])
+    prediction = model.predict(new_question_vector)
+    return str(prediction[0])
+
+iface = gr.Interface(fn=classify_text, inputs="text", outputs="label",title="Tabibu Bot",
+                        interpretation="default", examples=[
+                            ["I am feeling depressed"],
+                            ["I am feeling anxious"],
+                            ["I am feeling stressed"],
+                            ["I am feeling sad"],
+                        ])
+iface.launch()