app.py

# -*- coding: utf-8 -*-
"""PRML_project.ipynb

Automatically generated by Colab.

Original file is located at
    https://colab.research.google.com/drive/1_9mr_G1Wt8bteyyMEFJYBImPcIteTcSQ

## Downloading & preparing the Dataset
"""

import pandas as pd
import matplotlib.pyplot as plt
import warnings
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score,classification_report, ConfusionMatrixDisplay
import re
import string
from sklearn.linear_model import LogisticRegression
from sklearn.naive_bayes import MultinomialNB
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier, AdaBoostClassifier
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.svm import SVC
# Ignore FutureWarning messages
warnings.simplefilter(action='ignore', category=FutureWarning)

import os
import sys
from tempfile import NamedTemporaryFile
from urllib.request import urlopen
from urllib.parse import unquote, urlparse
from urllib.error import HTTPError
from zipfile import ZipFile
import tarfile
import shutil

CHUNK_SIZE = 40960
DATA_SOURCE_MAPPING = 'sentiment-analysis-dataset:https%3A%2F%2Fstorage.googleapis.com%2Fkaggle-data-sets%2F989445%2F1808590%2Fbundle%2Farchive.zip%3FX-Goog-Algorithm%3DGOOG4-RSA-SHA256%26X-Goog-Credential%3Dgcp-kaggle-com%2540kaggle-161607.iam.gserviceaccount.com%252F20240418%252Fauto%252Fstorage%252Fgoog4_request%26X-Goog-Date%3D20240418T100202Z%26X-Goog-Expires%3D259200%26X-Goog-SignedHeaders%3Dhost%26X-Goog-Signature%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'

KAGGLE_INPUT_PATH='/kaggle/input'
KAGGLE_WORKING_PATH='/kaggle/working'
KAGGLE_SYMLINK='kaggle'

import subprocess
subprocess.run(["umount", "/kaggle/input/"], stderr=subprocess.DEVNULL)
shutil.rmtree('/kaggle/input', ignore_errors=True)
os.makedirs(KAGGLE_INPUT_PATH, 0o777, exist_ok=True)
os.makedirs(KAGGLE_WORKING_PATH, 0o777, exist_ok=True)

try:
  os.symlink(KAGGLE_INPUT_PATH, os.path.join("..", 'input'), target_is_directory=True)
except FileExistsError:
  pass
try:
  os.symlink(KAGGLE_WORKING_PATH, os.path.join("..", 'working'), target_is_directory=True)
except FileExistsError:
  pass

for data_source_mapping in DATA_SOURCE_MAPPING.split(','):
    directory, download_url_encoded = data_source_mapping.split(':')
    download_url = unquote(download_url_encoded)
    filename = urlparse(download_url).path
    destination_path = os.path.join(KAGGLE_INPUT_PATH, directory)
    try:
        with urlopen(download_url) as fileres, NamedTemporaryFile() as tfile:
            total_length = fileres.headers['content-length']
            print(f'Downloading {directory}, {total_length} bytes compressed')
            dl = 0
            data = fileres.read(CHUNK_SIZE)
            while len(data) > 0:
                dl += len(data)
                tfile.write(data)
                done = int(50 * dl / int(total_length))
                sys.stdout.write(f"\r[{'=' * done}{' ' * (50-done)}] {dl} bytes downloaded")
                sys.stdout.flush()
                data = fileres.read(CHUNK_SIZE)
            if filename.endswith('.zip'):
              with ZipFile(tfile) as zfile:
                zfile.extractall(destination_path)
            else:
              with tarfile.open(tfile.name) as tarfile:
                tarfile.extractall(destination_path)
            print(f'\nDownloaded and uncompressed: {directory}')
    except HTTPError as e:
        print(f'Failed to load (likely expired) {download_url} to path {destination_path}')
        continue
    except OSError as e:
        print(f'Failed to load {download_url} to path {destination_path}')
        continue

print('Data source import complete.')

import numpy as np # linear algebra
import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)


import os
for dirname, _, filenames in os.walk('/kaggle/input'):
    for filename in filenames:
        print(os.path.join(dirname, filename))

d = pd.read_csv('/kaggle/input/sentiment-analysis-dataset/train.csv',encoding='latin1');
f = pd.read_csv('/kaggle/input/sentiment-analysis-dataset/test.csv',encoding='latin1');
df = pd.concat([d,f])

print(df.shape)
display(df.info())
display(df)

"""## Preprocessing the dataset"""

df.dropna(inplace=True)

df['sentiment'].value_counts(normalize=True).plot(kind='bar');

df['sentiment'] = df['sentiment'].astype('category').cat.codes
df['sentiment'].value_counts(normalize=True).plot(kind='bar');

df['Time of Tweet'] = df['Time of Tweet'].astype('category').cat.codes
# Convert Country column to categorical variable
df['Country'] = df['Country'].astype('category').cat.codes
# convert Age of User to integer
df['Age of User']=df['Age of User'].replace({'0-20':18,'21-30':25,'31-45':38,'46-60':53,'60-70':65,'70-100':80})

df.info()

df.drop(columns=['textID','Time of Tweet', 'Age of User', 'Country', 'Population -2020', 'Land Area (Km²)', 'Density (P/Km²)'])

def wp(text):
    text = text.lower()
    text = re.sub('\[.*?\]', '', text)
    text = re.sub("\\W"," ",text)
    text = re.sub('https?://\S+|www\.\S+', '', text)
    text = re.sub('<.*?>+', '', text)
    text = re.sub('[%s]' % re.escape(string.punctuation), '', text)
    text = re.sub('\n', '', text)
    text = re.sub('\w*\d\w*', '', text)
    return text

df['selected_text'] = df["selected_text"].apply(wp)

"""## Training and testing split  """

X=df['selected_text']
y= df['sentiment']

X_train, X_test, y_train, y_test = train_test_split(X,y,test_size=0.2,random_state=42)
print(X_train.shape)
print(X_test.shape)
print(y_train.shape)
print(y_test.shape)

vectorization = TfidfVectorizer()
XV_train = vectorization.fit_transform(X_train)
XV_test = vectorization.transform(X_test)

"""# Logistic Regression"""

logistic_model = LogisticRegression(max_iter=100)

logistic_model.fit(XV_train, y_train)

y_pred_logistic = logistic_model.predict(XV_test)

accuracy_logistic = accuracy_score(y_test, y_pred_logistic)
print("Logistic Regression Model:")
print(f"Accuracy: {accuracy_logistic}")

report_logistic = classification_report(y_test, y_pred_logistic)
print("Logistic Regression Classification Report:")
print(report_logistic)

ConfusionMatrixDisplay.from_predictions(y_test,y_pred_logistic);

pip install gradio

import gradio as gr
import matplotlib.pyplot as plt
import seaborn as sns

# Function to classify sentiment
def classify_sentiment(text):
    # Preprocess the text
    processed_text = wp(text)
    # Vectorize the text
    vectorized_text = vectorization.transform([processed_text])
    # Predict sentiment using logistic regression model
    prediction = logistic_model.predict(vectorized_text)[0]
    # Output sentiment label
    sentiment_label = output_label(prediction)
    # Get probabilities for each sentiment class
    probabilities = logistic_model.predict_proba(vectorized_text)[0]

    # Plot probabilities
    plt.figure(figsize=(8, 6))
    sns.barplot(x=["Negative", "Neutral", "Positive"], y=probabilities)
    plt.xlabel("Sentiment")
    plt.ylabel("Probability")
    plt.title("Sentiment Probability Distribution")
    plt.ylim([0, 1])
    plt.tight_layout()
    plt.savefig("sentiment_probabilities.png")

    return sentiment_label, "sentiment_probabilities.png"

# Input and output components for the interface
inputs = gr.Textbox(lines=10, label="Enter the text you want to analyze:")
outputs = [
    gr.Textbox(label="Sentiment Prediction"),
    gr.Image(label="Sentiment Probability Distribution")
]

# Create the Gradio interface
interface = gr.Interface(fn=classify_sentiment, inputs=inputs, outputs=outputs, title="Sentiment Classification", description="Enter a piece of text and analyze its sentiment.")
interface.launch()