# Load necessary libraries

import spacy

from spacytextblob.spacytextblob import SpacyTextBlob

import numpy as np

import pandas as pd

# Load spaCy model and add textblob pipeline

nlp $=$ spacy.load $(\text{'}$en$\_$core$\_$web$\_$sm$\text{'})$

nlp$.$add$\_$pipe $(\text{'}$spacytextblob$\text{'})$

# Read the CSV file

dataframe $=$ pd$.$read$\_$csv$($r$"$C:$\backslash$Users$\backslash$User$\backslash$OneDrive$\backslash$Desktop$\backslash 1429\_1.$csv$")$

# Remove missing values and replace NaN with empty string

clean$\_$data $=$ dataframe.dropna$($subset$=[\text{'}$reviews$.$text'$]).$fillna$(\text{'}\text{'})$

# Function to preprocess text

def preprocess$\_$text$($text$)$:

if isinstance $($text$,$ str$)$:

doc $=nlp($text$)$

tokens $=[$token$.$text.lower$().$strip$()$ for token in doc if not

token.is$\_$stop$]$

return $\text{'}\text{'}.$join$($tokens$)$

else:

return $\text{'}\text{'}$

# Apply preprocessing to 'reviews.text' column

dataframe $[\text{'}$reviews$.$text'$]=$

clean$\_$data $[\text{'}$reviews$.$text'$].$apply $($preprocess$\_$text$)$

# Function for sentiment analysis

def analyze sentiment$($review$)$:

doc $=\frac{n}{b}ar(l)p($review$)$

sentiment $=$ doc.$\_.$sentiment$.$polarity

if sentiment $>0\mathrm{.}5$ :

return 'Positive'

elif sentiment :

return 'Negative'

else:

return 'Neutral'

# Function to test sentiment analysis

def test$\_$sentiment$\_$analysis $($review$)$:

sentiment$\_$result $=$ analyze$\_$sentiment $($review$)$

print $($f$"$Review: $\{$review$\}")$

print$($f$"$Sentiment: $\{$sentiment$\_$result$\}")$

print$("="*30$