File size: 3,864 Bytes
9116a7d 5386b06 9116a7d |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 |
# import libraries
import streamlit as st
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
import joblib
from sklearn.metrics import accuracy_score, classification_report, confusion_matrix
from sklearn.model_selection import train_test_split
#load model
import joblib
@st.cache_resource # Caches the model in Streamlit's memory
def load_model():
return joblib.load("SA_model.pkl") # Ensure your model is saved and available
model = load_model()
#load dataset
df = pd.read_csv('Tweets.csv', encoding='utf-8')
X = df['text']
y = df['airline_sentiment']
X_train, X_test, y_train, y_test = train_test_split(
X, y , test_size=0.33, random_state=42
)
#compute sentiment
class_report_data = {
"Precision": [0.67, 0.51, 0.88],
"Recall": [0.73, 0.64, 0.79],
"F1-score": [0.70, 0.57, 0.83]
}
# Properly structured DataFrame
class_report_df = pd.DataFrame(class_report_data, index=["Positive", "Neutral", "Negative"])
#predict text sentiment
def predict_sentiment(text):
if isinstance(text, str):
text = [text] # Ensure input is a list
prediction = model.predict(text) # Get numerical prediction
# Mapping numerical labels to sentiment categories
sentiment_mapping = {0: "Negative", 1: "Neutral", 2: "Positive"}
return sentiment_mapping.get(prediction[0], "Unknown") # Convert number to label
#Model Introduction
st.title('📌 Sentiment Analysis Web Application')
st.markdown(
"""
## 📖 Introduction
Welcome to the **Sentiment Analysis Web Application**! This tool is designed to analyze the sentiment of text messages
using a **Support Vector Machine (SVM) model**. The model has been trained on the **Airline Tweets dataset from Kaggle**
and classifies text into three sentiment categories:
- ✅ **Positive**
- ❌ **Negative**
- ⚖ **Neutral**
"""
)
#Tab Structuring
tab1, tab2, tab3 = st.tabs(['📊 Dataset Preview', '📈 Model Performance', '🔍 Sentiment Prediction'])
with tab1:
st.markdown(
"""
## 📊 Dataset Preview
The dataset used for training this model consists of tweets related to airline services. Each tweet is labeled
with one of the three sentiment categories (**Positive, Negative, or Neutral**). Below is a sample of the dataset:
"""
)
st.write (df)
with tab2:
st.markdown(
"""
## 📈 Model Performance
Below are the key performance metrics of the trained **Support Vector Machine (SVM)** model:
- **Model Accuracy**: The percentage of correctly classified instances.
- **Classification Report**: Includes precision and recall for each sentiment class.
- **Confusion Matrix**: A visual representation comparing actual versus predicted classifications.
"""
)
st.write(f"**📌 Model Accuracy:** 75%")
st.markdown("### 📋 Classification Report")
st.dataframe(class_report_df)
st.markdown("### 🔢 Confusion Matrix")
# Load and display confusion matrix image
try:
st.image("cmap.png", caption="Confusion Matrix", use_container_width=True)
except FileNotFoundError:
st.warning("⚠️ Confusion matrix image not found. Please check the file path.")
with tab3:
st.markdown(
"""
## 🔍 Sentiment Prediction
Type a sentence in the text box below, and the model will classify it as **Positive, Neutral, or Negative**.
"""
)
user_input = st.text_area("Type your sentence here:", "")
if st.button("🔎 Analyze Sentiment"):
if user_input.strip():
sentiment_result = predict_sentiment(user_input)
st.success(f"### 🎯 Prediction: **{sentiment_result}**")
else:
st.warning("⚠️ Please enter a valid text input.")
|