# Description: This script performs sentiment analysis on the Amazon product reviews dataset using spaCy and TextBlob.

# Load spaCy model

import spacy

from spacytextblob.spacytextblob import SpacyTextBlob

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

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

import numpy as np

import pandas as pd

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

dataframe.head$()$

$"""$Preprocessing the text data"""

# Select 'review.text' column

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

# Remove missing values

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

# Function to apply preprocessing to the 'reviews.text' column using $.$loc

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

# Use spaCy to tokenize and remove stopwords

doc $=$ nlp$($text$)$

tokens $=[$token$.$text.lower$().$strip$()$ for token in doc if not token.is$\_$stop$]$

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

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

dataframe$[\text{'}$reviews$.$text'$]=$ dataframe$[\text{'}$reviews$.$text'$].$apply$($preprocess$\_$text$)$

# Function for sentiment analysis

def analyze$\_$sentiment$($review$)$:

# Process the review using spaCy

doc $=$ nlp$($review$)$

# Get sentiment using the $.$sentiment attribute

sentiment $=$ doc.sentiment

# Determine sentiment category $($positive$,$ negative, or neutral$)$

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

return 'Positive'

elif sentiment :

return 'Negative'

else:

return 'Neutral'

# Text usage

sample$\_$review $=$ "I love this product. It's amazing!"

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

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

$"""$# $**$Test the model for Sample Model Reviews$**"""$

# Example usage of the sentiment analysis function

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

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

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

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

print$("="*30)$

# Choose two reviews for testing $($make sure the indices are valid$)$

review$\_$index$\_1=0$

review$\_$index$\_2=1$

# Retrieve the reviews using indexing

review$\_1=$ dataframe$[\text{'}$reviews$.$text'$][$review$\_$index$\_1]$

review$\_2=$ dataframe$[\text{'}$reviews$.$text'$][$review$\_$index$\_2]$

# Test the sentiment analysis function on the selected reviews

test$\_$sentiment$\_$analysis$($review$\_1)$

test$\_$sentiment$\_$analysis$($review$\_2)$

# Compare the similarity of the two reviews using spaCy similarity

similarity$\_$score $=$ nlp$($review$\_1).$similarity$($nlp$($review$\_2))$

print$($f$"$Similarity Score: $\{$similarity$\_$score$\}")$

Error:PROBLEMS OUTPUT DEBUG CONSOLE TERMINAL PORTS

Python

py$"$

$r$ set low$\_$memory$=$False.

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

Traceback $($most recent call last$)$:

dataframe$[\text{'}$reviews$.$text'$]=$ dataframe$[\text{'}$reviews$.$text'$].$apply$($preprocess$\_$text$)$

$.$ apply$()$

return self.apply$\_$standard$()$

mapped $=$ obj.$\_$map$\_$values $($

an$$na$$nananananan

return algorithms.map$\_$array$($arr$,$ mapper, na$\_$action$=$na$\_$action, convert$=$convert$)$

return lib.map$\_$infer$($values$,$ mapper, convert$=$convert$)$

File "lib.pyx$",$ line $2972,$ in pandas.$\_$libs.lib.map$\_$infer

doc $=$ nlp$($text$)$

$1($

doc $=$ self.$\_$ensure$\_$doc$($text$)$

raise ValueError$($Errors$.$E$1041.$format$($type$=$type$($doc$\_$like$)))$

ValueError: $[$E$1041]$ Expected a string, Doc, or bytes as input, but got: $$class 'float'$>$

PS C: VUsers $\backslash$User$>$ What do these mean and how do I correct these?