Duplicate from bright1/sentiment-analysis-app-gradio

Co-authored-by: Bright Eshun <bright1@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,13 @@
+---
+title: Sentiment Analysis App Gradio
+emoji: 📉
+colorFrom: gray
+colorTo: gray
+sdk: gradio
+sdk_version: 3.28.0
+app_file: app.py
+pinned: false
+duplicated_from: bright1/sentiment-analysis-app-gradio
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,77 @@
+import gradio as gr
+import numpy as np
+import pandas as pd
+from transformers import AutoTokenizer, AutoConfig,AutoModelForSequenceClassification
+from scipy.special import softmax
+import os
+
+# Requirements
+def load_distilbert():
+    model_path = "bright1/fine-tuned-distilbert-base-uncased"
+    tokenizer = AutoTokenizer.from_pretrained(model_path)
+    # config = AutoConfig.from_pretrained(model_path)
+    model = AutoModelForSequenceClassification.from_pretrained(model_path)
+    return model, tokenizer
+
+def load_roberta():
+    model_path = "bright1/fine-tuned-twitter-Roberta-base-sentiment"
+    tokenizer = AutoTokenizer.from_pretrained(model_path)
+    # config = AutoConfig.from_pretrained(model_path)
+    model = AutoModelForSequenceClassification.from_pretrained(model_path)
+    return model, tokenizer
+
+# def check_csv(csv_file, data):
+#     if os.path.isfile(csv_file):
+#         data.to_csv(csv_file, mode='a', header=False, index=False, encoding='utf-8')
+#     else:
+#         history = data.copy()
+#         history.to_csv(csv_file, index=False)
+
+#Preprocess text
+def preprocess(text):
+    new_text = []
+    for t in text.split(" "):
+        t = "@user" if t.startswith("@") and len(t) > 1 else t
+        t = "http" if t.startswith("http") else t
+        print(t)
+        new_text.append(t)
+    print(new_text)
+
+    return " ".join(new_text)
+
+#Process the input and return prediction
+def sentiment_analysis(model_type, text):
+    if model_type== 'distilbert':
+        model, tokenizer  = load_distilbert()
+    else:
+        model, tokenizer = load_roberta()
+    save_text =  {'tweet': text}
+    text = preprocess(text)
+    encoded_input = tokenizer(text, return_tensors = "pt") # for PyTorch-based models
+    output = model(**encoded_input)
+    scores_ = output[0][0].detach().numpy()
+    scores_ = softmax(scores_)
+
+    # Format output dict of scores
+    labels = ["Negative", "Neutral", "Positive"]
+    scores = {l:float(s) for (l,s) in zip(labels, scores_) }
+    # save_text.update(scores)
+    # user_data = {key: [value] for key,value in save_text.items()}
+    # data = pd.DataFrame(user_data,)
+    # check_csv('history.csv', data)
+    # hist_df = pd.read_csv('history.csv')
+    return scores
+# , hist_df.head()
+
+model_type = gr.Radio(choices=['distilbert', 'roberta'], label='Select model type', value='roberta' )  
+#Gradio app interface
+#Gradio app interface
+demo = gr.Interface(fn = sentiment_analysis,
+                   inputs = [model_type, gr.TextArea("Write your text or tweet here", label="Analyze your COVID-19 tweets" )],
+                   outputs = ["label"],
+                   title = "COVID-19 Vaccine Tweet Analyzer App",
+                   description  = "COVID-19 Tweets Analyzer",
+                   interpretation = "default",
+                   examples = [["roberta", "Being vaccinated is actually awesome :)"]]
+                   ).launch()
+

requirements.txt

@@ -0,0 +1,13 @@
+nltk
+torch 
+gradio
+datasets==2.12.0
+numpy==1.22.4
+pandas==1.5.3
+scikit-learn==1.2.2
+transformers==4.28.1
+wandb==0.15.0
+IPython==7.34.0
+jupyter_client==6.1.12
+jupyter_core==5.3.0
+notebook==6.4.8