sentiment_analysis (1).py

# -*- coding: utf-8 -*-
"""Sentiment Analysis.ipynb

Automatically generated by Colab.

Original file is located at
    https://colab.research.google.com/drive/1BcGnaVR6A3UQjUEBEKrn5ay0tlOAYRqC
"""

pip install pandas numpy nltk transformers scikit-learn matplotlib bertopic

import pandas as pd

# Load the dataset (replace 'dataset.csv' with your file path)
data = pd.read_csv('/content/sample_dataset.csv')

# Display the first few rows
print(data.head())

# Check if the dataset has null values
print(data.isnull().sum())

# Drop rows with missing values
data.dropna(inplace=True)

import re
import nltk
from nltk.corpus import stopwords
nltk.download('stopwords')
nltk.download('punkt')

# Define preprocessing function
def preprocess_text(text):
    # Remove URLs, mentions, hashtags, and special characters
    text = re.sub(r"http\S+|@\S+|#\S+", "", text)
    text = re.sub(r"[^a-zA-Z\s]", "", text)
    text = text.lower()

    # Remove stopwords
    words = text.split()
    stop_words = set(stopwords.words('english'))
    words = [word for word in words if word not in stop_words]

    return " ".join(words)

# Apply preprocessing to the dataset
data['Cleaned_Text'] = data['text_column'].apply(preprocess_text)  # Replace 'text_column' with the actual column name containing text
print(data.head())

from transformers import pipeline

# Load the sentiment analysis model
sentiment_pipeline = pipeline("sentiment-analysis")

# Predict sentiment for each cleaned text
data['Sentiment'] = data['Cleaned_Text'].apply(lambda x: sentiment_pipeline(x)[0]['label'])
print(data[['Cleaned_Text', 'Sentiment']].head())

import matplotlib

from bertopic import BERTopic

# Fit BERTopic to the cleaned text
topic_model = BERTopic()
topics, _ = topic_model.fit_transform(data['Cleaned_Text'])

# Add topics to the dataset
data['Topic'] = topics

# Display topic information
print(topic_model.get_topic_info())

# Save the dataset with predictions and topics
data.to_csv('/content/sentiment_dashboard.csv', index=False)
print("Results saved to sentiment_dashboard.csv")

import os
import pandas as pd
from transformers import pipeline

# Define the folder path
folder_path = r"C:\Users\anilr\OneDrive\Desktop\sentiment results"
file_name = "sentiment_results.csv"

# Check if the folder exists; create if not
if not os.path.exists(folder_path):
    os.makedirs(folder_path)

# Define file path
file_path = os.path.join(folder_path, file_name)

# Example data for sentiment analysis (replace with your own dataset)
example_data = [
    "I love this product! It's amazing.",
    "This is the worst experience I've ever had.",
    "Completely neutral about this, it's okay.",
    "Highly recommend this to everyone!",
    "Terrible service, I won't come back.",
]

# Load sentiment analysis pipeline
sentiment_pipeline = pipeline("sentiment-analysis")

# Analyze sentiments
sentiments = []
for text in example_data:
    result = sentiment_pipeline(text)[0]
    sentiments.append({"Text": text, "Sentiment": result['label'], "Confidence": result['score']})

# Create a DataFrame
df = pd.DataFrame(sentiments)

# Save DataFrame to CSV
df.to_csv(file_path, index=False)

print(f"Sentiment results saved to {file_path}")

pip install streamlit

from google.colab import files
uploaded = files.upload()

# After uploading, load the dataset using pandas
import pandas as pd

# Assuming the file is named 'dataset.csv', replace it with the actual filename
data = pd.read_csv('/content/sample_dataset.csv')

# Display the first few rows
print(data.head())

from google.colab import drive
drive.mount('/content/drive')

# Assuming the dataset is in the folder "MyDrive" and is named "dataset.csv"
data = pd.read_csv('/content/sample_dataset.csv')

# Display the first few rows
print(data.head())

import csv

# Assume 'data_to_export' is a list of dictionaries

# Check if the dataset has null values
print(data.isnull().sum())

# Optionally, check for the shape of the dataset
print("Shape of the dataset:", data.shape)

# Drop rows with missing values
data.dropna(inplace=True)

# Verify if the missing values are removed
print(data.isnull().sum())

# Upload dataset (from local machine)
from google.colab import files
uploaded = files.upload()

# Load the dataset
import pandas as pd
data = pd.read_csv('/content/sample_dataset.csv')  # Replace with your actual filename

# Display the first few rows of the dataset
print(data.head())

# Check if the dataset has null values
print(data.isnull().sum())

# Drop rows with missing values
data.dropna(inplace=True)

# Verify if the missing values are removed
print(data.isnull().sum())

from google.colab import drive
drive.mount('/content/drive')

# Load the dataset from your Google Drive
data = pd.read_csv('/content/sample_dataset.csv')  # Replace with your actual path

# Display the first few rows
print(data.head())

# Check for null values
print(data.isnull().sum())

# Drop rows with missing values
data.dropna(inplace=True)

# Verify if the missing values are removed
print(data.isnull().sum())

import re
import nltk
from nltk.corpus import stopwords
nltk.download('stopwords')
nltk.download('punkt')

# Define preprocessing function
def preprocess_text(text):
    # Remove URLs, mentions, hashtags, and special characters
    text = re.sub(r"http\S+|@\S+|#\S+", "", text)
    text = re.sub(r"[^a-zA-Z\s]", "", text)
    text = text.lower()

    # Remove stopwords
    words = text.split()
    stop_words = set(stopwords.words('english'))
    words = [word for word in words if word not in stop_words]

    return " ".join(words)

# Apply preprocessing to the dataset
data['Cleaned_Text'] = data['text_column'].apply(preprocess_text)  # Replace 'text_column' with your actual column name
print(data.head())

from transformers import pipeline

# Load the sentiment analysis model
sentiment_pipeline = pipeline("sentiment-analysis")

# Predict sentiment for each cleaned text
data['Sentiment'] = data['Cleaned_Text'].apply(lambda x: sentiment_pipeline(x)[0]['label'])
print(data[['Cleaned_Text', 'Sentiment']].head())

import matplotlib.pyplot as plt

from transformers import pipeline
import pandas as pd

# Load the dataset
data = pd.read_csv('/content/sample_dataset.csv')  # Replace with your file path

# Load the sentiment analysis pipeline
sentiment_pipeline = pipeline("sentiment-analysis")

# Apply sentiment analysis to each row in the 'text_column'
data['Sentiment'] = data['text_column'].apply(lambda x: sentiment_pipeline(x)[0]['label'])

# Optionally, save the result with sentiment labels back to CSV
data.to_csv('/content/sentiment_analysis_results.csv', index=False)

# Display the data with predicted sentiment
print(data[['text_column', 'Sentiment']].head())

import matplotlib as plt

sentiment_pipeline = pipeline("sentiment-analysis", model="distilbert/distilbert-base-uncased-finetuned-sst-2-english", revision="714eb0f")

from transformers import pipeline

sentiment_pipeline = pipeline("sentiment-analysis", model="distilbert/distilbert-base-uncased-finetuned-sst-2-english", revision="714eb0f")

from transformers import pipeline

# Load the sentiment analysis model
sentiment_pipeline = pipeline("sentiment-analysis")

# Function to get sentiment for user input
def get_sentiment(input_text):
    result = sentiment_pipeline(input_text)
    sentiment = result[0]['label']
    confidence = result[0]['score']
    return sentiment, confidence

# Get user input
user_input = input("Enter a sentence for sentiment analysis: ")

# Get the sentiment prediction
sentiment, confidence = get_sentiment(user_input)

# Output the result
print(f"Sentiment: {sentiment}")
print(f"Confidence score: {confidence:.4f}")