Spaces:
Runtime error
Runtime error
Merge pull request #1 from Youranalyst-coder/codex/apply-changes-from-referenced-repository
Browse files- README.md +17 -7
- app/app.py +78 -16
README.md
CHANGED
|
@@ -1,27 +1,37 @@
|
|
| 1 |
# π¬ Twitter Sentiment Analyzer
|
| 2 |
|
| 3 |
-
A machine learning project that predicts
|
| 4 |
|
| 5 |
## π§ Tech Stack
|
| 6 |
|
| 7 |
- Python, Pandas, Scikit-learn, NLTK
|
| 8 |
- TF-IDF Vectorization
|
| 9 |
-
- Logistic Regression
|
| 10 |
-
- Streamlit (Web App
|
| 11 |
|
| 12 |
## π Features
|
| 13 |
|
| 14 |
-
- Text preprocessing
|
| 15 |
-
-
|
| 16 |
-
-
|
| 17 |
|
| 18 |
## β
Try it
|
| 19 |
|
| 20 |
-
|
| 21 |
|
| 22 |
## π How to Run
|
| 23 |
|
| 24 |
```bash
|
| 25 |
pip install -r requirements.txt
|
| 26 |
streamlit run app/app.py
|
|
|
|
| 27 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# π¬ Twitter Sentiment Analyzer
|
| 2 |
|
| 3 |
+
A machine learning project that predicts whether a tweet is **positive**, **neutral**, or **negative** using natural language processing and logistic regression.
|
| 4 |
|
| 5 |
## π§ Tech Stack
|
| 6 |
|
| 7 |
- Python, Pandas, Scikit-learn, NLTK
|
| 8 |
- TF-IDF Vectorization
|
| 9 |
+
- Multiclass Logistic Regression
|
| 10 |
+
- Streamlit (Web App UI)
|
| 11 |
|
| 12 |
## π Features
|
| 13 |
|
| 14 |
+
- Text preprocessing and model training notebooks
|
| 15 |
+
- Trained logistic regression pipeline for three-way sentiment detection
|
| 16 |
+
- Streamlit UI that displays the predicted class and class probabilities
|
| 17 |
|
| 18 |
## β
Try it
|
| 19 |
|
| 20 |
+
Deploy the `app/app.py` Streamlit interface or use the provided pickle files directly in your own project.
|
| 21 |
|
| 22 |
## π How to Run
|
| 23 |
|
| 24 |
```bash
|
| 25 |
pip install -r requirements.txt
|
| 26 |
streamlit run app/app.py
|
| 27 |
+
```
|
| 28 |
|
| 29 |
+
## π§ Training Artifacts
|
| 30 |
+
|
| 31 |
+
The repository contains pretrained artifacts inside the `app/` and root directories:
|
| 32 |
+
|
| 33 |
+
- `app/logistic_model.pkl` β Multiclass logistic regression estimator
|
| 34 |
+
- `app/tfidf_vectorizer.pkl` β Fitted TF-IDF vectorizer compatible with the model
|
| 35 |
+
- `sentiment_model.pkl` β End-to-end Scikit-learn pipeline (vectorizer + classifier)
|
| 36 |
+
|
| 37 |
+
These are generated from the notebook in `notebooks/sentiment_model.ipynb`.
|
app/app.py
CHANGED
|
@@ -1,25 +1,87 @@
|
|
| 1 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
import joblib
|
| 3 |
-
import
|
|
|
|
|
|
|
| 4 |
|
| 5 |
-
|
| 6 |
-
|
| 7 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
|
| 9 |
-
model = joblib.load(model_path)
|
| 10 |
-
vectorizer = joblib.load(vectorizer_path)
|
| 11 |
|
| 12 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
|
| 14 |
-
user_input = st.text_area("Enter your tweet or sentence here:")
|
| 15 |
|
| 16 |
-
|
| 17 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 18 |
st.warning("Please enter some text to analyze.")
|
| 19 |
else:
|
| 20 |
-
|
| 21 |
-
|
| 22 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 23 |
|
| 24 |
-
|
| 25 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
from __future__ import annotations
|
| 2 |
+
|
| 3 |
+
from pathlib import Path
|
| 4 |
+
from typing import Dict, Tuple
|
| 5 |
+
|
| 6 |
import joblib
|
| 7 |
+
import pandas as pd
|
| 8 |
+
import streamlit as st
|
| 9 |
+
|
| 10 |
|
| 11 |
+
@st.cache_resource
|
| 12 |
+
def load_artifacts() -> Tuple[object, object]:
|
| 13 |
+
"""Load the trained sentiment model and TF-IDF vectorizer."""
|
| 14 |
+
artifacts_dir = Path(__file__).resolve().parent
|
| 15 |
+
model = joblib.load(artifacts_dir / "logistic_model.pkl")
|
| 16 |
+
vectorizer = joblib.load(artifacts_dir / "tfidf_vectorizer.pkl")
|
| 17 |
+
return model, vectorizer
|
| 18 |
|
|
|
|
|
|
|
| 19 |
|
| 20 |
+
def predict_sentiment(text: str) -> Tuple[str, float, Dict[str, float]]:
|
| 21 |
+
"""Predict the sentiment label and probability distribution for the text."""
|
| 22 |
+
model, vectorizer = load_artifacts()
|
| 23 |
+
features = vectorizer.transform([text])
|
| 24 |
+
probabilities = model.predict_proba(features)[0]
|
| 25 |
+
classes = model.classes_
|
| 26 |
+
class_probabilities = {label: prob for label, prob in zip(classes, probabilities)}
|
| 27 |
+
top_label = max(class_probabilities, key=class_probabilities.get)
|
| 28 |
+
top_score = class_probabilities[top_label]
|
| 29 |
+
return top_label, top_score, class_probabilities
|
| 30 |
|
|
|
|
| 31 |
|
| 32 |
+
SENTIMENT_DISPLAY = {
|
| 33 |
+
"positive": {
|
| 34 |
+
"title": "Positive",
|
| 35 |
+
"emoji": "π",
|
| 36 |
+
"description": "The tweet expresses a favourable or uplifting sentiment.",
|
| 37 |
+
},
|
| 38 |
+
"neutral": {
|
| 39 |
+
"title": "Neutral",
|
| 40 |
+
"emoji": "π",
|
| 41 |
+
"description": "The tweet is balanced without a clear positive or negative leaning.",
|
| 42 |
+
},
|
| 43 |
+
"negative": {
|
| 44 |
+
"title": "Negative",
|
| 45 |
+
"emoji": "π",
|
| 46 |
+
"description": "The tweet carries criticism, frustration, or an unfavourable view.",
|
| 47 |
+
},
|
| 48 |
+
}
|
| 49 |
+
|
| 50 |
+
|
| 51 |
+
st.set_page_config(page_title="Twitter Sentiment Analysis", page_icon="π¬")
|
| 52 |
+
st.title("π¬ Twitter Sentiment Analysis")
|
| 53 |
+
st.write(
|
| 54 |
+
"Enter a tweet below and the model will classify it as positive, neutral, or negative."
|
| 55 |
+
)
|
| 56 |
+
|
| 57 |
+
user_input = st.text_area(
|
| 58 |
+
"Tweet text",
|
| 59 |
+
placeholder="I love how friendly everyone is on Twitter today!",
|
| 60 |
+
height=150,
|
| 61 |
+
)
|
| 62 |
+
|
| 63 |
+
if st.button("Predict Sentiment", type="primary"):
|
| 64 |
+
if not user_input.strip():
|
| 65 |
st.warning("Please enter some text to analyze.")
|
| 66 |
else:
|
| 67 |
+
label, score, probabilities = predict_sentiment(user_input)
|
| 68 |
+
details = SENTIMENT_DISPLAY.get(label, {"title": label.title(), "emoji": "", "description": ""})
|
| 69 |
+
|
| 70 |
+
st.success(
|
| 71 |
+
f"{details['emoji']} **{details['title']}** sentiment detected with a confidence of {score:.1%}."
|
| 72 |
+
)
|
| 73 |
+
if details.get("description"):
|
| 74 |
+
st.caption(details["description"])
|
| 75 |
|
| 76 |
+
sorted_probabilities = sorted(probabilities.items(), key=lambda item: item[1], reverse=True)
|
| 77 |
+
probability_frame = pd.DataFrame(
|
| 78 |
+
{
|
| 79 |
+
"Sentiment": [SENTIMENT_DISPLAY[label]["title"] for label, _ in sorted_probabilities],
|
| 80 |
+
"Probability": [score for _, score in sorted_probabilities],
|
| 81 |
+
}
|
| 82 |
+
)
|
| 83 |
+
probability_frame["Probability"] = probability_frame["Probability"].map(lambda p: f"{p:.1%}")
|
| 84 |
+
st.subheader("Class Probabilities")
|
| 85 |
+
st.dataframe(probability_frame, hide_index=True, width='stretch')
|
| 86 |
+
else:
|
| 87 |
+
st.info("Click **Predict Sentiment** to get a prediction.")
|