created project

app.py

@@ -0,0 +1,32 @@
+import streamlit as st
+import data
+import models
+
+def main():
+    st.title("CSV Sentiment Analysis")
+
+    uploaded_file = st.file_uploader("Upload CSV or Excel file", type=["csv", "xlsx"])
+    classifier = models.load_model()
+    df = data.read_data(uploaded_file)
+    
+    if uploaded_file:
+        column = list(df.columns)
+        column_with_empty = [""] + column 
+        text_to_analyze = st.selectbox("Select text column", column_with_empty)
+
+
+
+        if text_to_analyze in df.columns:
+            text_column = text_to_analyze 
+
+            if text_column:
+            
+                df = models.analyze_sentiments(df, text_column, classifier)
+
+                data.visualize_data(df, st)
+            
+                st.subheader("Processed Data Preview")
+                st.dataframe(df.head())
+
+if __name__ == "__main__":
+    main()

data.py

@@ -0,0 +1,20 @@
+import pandas as pd
+import matplotlib.pyplot as plt
+
+def read_data(file):
+    try:
+        if file.name.endswith(".csv"):
+            data_frame = pd.read_csv(file)
+        elif file.name.endswith(".xlsx"):
+            data_frame = pd.read_excel(file)
+        return data_frame
+    except Exception as e:
+        return f"Unable to read the file : {file}. Error : {e}"
+    
+
+def visualize_data(df,st):
+    sentiment_counts = df['sentiment'].value_counts()
+    fig, ax = plt.subplots()
+    ax.pie(sentiment_counts, labels=sentiment_counts.index, autopct='%1.1f%%')
+    ax.axis('equal')
+    st.pyplot(fig)

models.py

@@ -0,0 +1,18 @@
+from transformers import pipeline
+
+def load_model():
+    return pipeline("text-classification", model="tabularisai/multilingual-sentiment-analysis")
+
+def analyze_sentiments(df, text_column, classifier):
+    if text_column not in df.columns:
+        raise ValueError(f"Column '{text_column}' not found in DataFrame.")
+    sentiments = []
+    for text in df[text_column]:
+        try:
+            sentiment = classifier(str(text))[0]['label']
+            sentiments.append(sentiment)
+        except Exception as e:
+            print(f"Error processing text: {text}. Error: {e}")
+            sentiments.append('UNKNOWN')
+    df['sentiment'] = sentiments
+    return df

requirements.txt

@@ -0,0 +1,6 @@
+torch --index-url https://download.pytorch.org/whl/cpu
+transformers
+streamlit
+pandas
+matplotlib 
+openpyxl