|
|
|
"""First_Text_Classification.ipynb |
|
|
|
Automatically generated by Colaboratory. |
|
|
|
Original file is located at |
|
https://colab.research.google.com/drive/1sdLss09e3OxYVoeK3oBA6qrUSj_iOxp- |
|
|
|
<h3 align = "center">Importing Libraries</h3> |
|
""" |
|
|
|
import numpy as np |
|
import pandas as pd |
|
|
|
"""<h3 align = "center">Importing Dataset</h3>""" |
|
|
|
data = pd.read_csv("spam.csv", encoding = "ISO-8859-1") |
|
|
|
"""<h3 align = "center">Preliminary Data Checks</h3>""" |
|
|
|
data.head() |
|
|
|
data.isnull().sum() |
|
|
|
data.shape |
|
|
|
data['v1'].value_counts() |
|
|
|
data.info() |
|
|
|
"""<h3 align = "center">Putting the Length of Characters of each row in a column.</h3>""" |
|
|
|
data["Unnamed: 2"] = data["v2"].str.len() |
|
|
|
"""<h3 align = "center">Visualising Length of Characters for each category!</h3>""" |
|
|
|
|
|
"""<h5>It is evident from the above plot that spam texts are usually longer in length!</h5> |
|
|
|
<h3 align = "center">Defining Variables</h3> |
|
""" |
|
|
|
X = data["v2"] |
|
y = data["v1"] |
|
|
|
"""<h3 align = "center">Train Test Split</h3>""" |
|
|
|
from sklearn.model_selection import train_test_split |
|
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.33, random_state=42) |
|
|
|
"""<h3 align = "center">Vecrorizing Words into Matrix</h3>""" |
|
|
|
from sklearn.feature_extraction.text import CountVectorizer |
|
count_vect = CountVectorizer() |
|
|
|
X_train_counts = count_vect.fit_transform(X_train) |
|
|
|
X_train_counts |
|
|
|
X_train.shape |
|
|
|
X_train_counts.shape |
|
|
|
from sklearn.feature_extraction.text import TfidfTransformer |
|
tfidf_transformer = TfidfTransformer() |
|
|
|
X_train_tfidf = tfidf_transformer.fit_transform(X_train_counts) |
|
|
|
X_train_tfidf.shape |
|
|
|
"""<h3 align = "center">Using TDIF Vectorizer for optimum vectorization!</h3>""" |
|
|
|
from sklearn.feature_extraction.text import TfidfVectorizer |
|
vectorizer = TfidfVectorizer() |
|
|
|
X_train_tfidf = vectorizer.fit_transform(X_train) |
|
|
|
X_train_tfidf.shape |
|
|
|
"""<h3 align = "center">Creating Model</h3>""" |
|
|
|
from sklearn.svm import LinearSVC |
|
clf = LinearSVC() |
|
|
|
clf.fit(X_train_tfidf,y_train) |
|
|
|
"""<h3 align = "center">Creating Pipeline</h3>""" |
|
|
|
from sklearn.pipeline import Pipeline |
|
|
|
text_clf = Pipeline([("tfidf",TfidfVectorizer()),("clf",LinearSVC())]) |
|
|
|
text_clf.fit(X_train,y_train) |
|
|
|
predictions = text_clf.predict(X_test) |
|
|
|
X_test |
|
|
|
from sklearn.metrics import confusion_matrix,classification_report,accuracy_score |
|
|
|
print(confusion_matrix(y_test,predictions)) |
|
|
|
print(classification_report(y_test,predictions)) |
|
|
|
"""<h3 align = "center">Accuracy Score</h3>""" |
|
|
|
print(accuracy_score(y_test,predictions)) |
|
|
|
"""<h3 align = "center">Predictions </h3>""" |
|
|
|
text_clf.predict(["Hi how are you doing today?"]) |
|
|
|
text_clf.predict(["Congratulations! You are selected for a free vouchar worth $500"]) |
|
|
|
"""<h3 align = "center">Creating User Interface!</h3>""" |
|
|
|
import gradio as gr |
|
|
|
def first_nlp_spam_detector(text): |
|
list = [] |
|
list.append(text) |
|
arr = text_clf.predict(list) |
|
if arr[0] == 'ham': |
|
return "Your Text is a Legitimate One!" |
|
else: |
|
return "Beware of such text messages, It\'s a Spam! " |
|
|
|
interface = gr.Interface(first_nlp_spam_detector,inputs = gr.Textbox(lines=2, placeholder="Enter your Text Here.....!", show_label = False), |
|
outputs = gr.Label(value = "Predicting the Text Classification..!"),description = "Predicting Text Legitimacy!") |
|
|
|
first_nlp_spam_detector("Congratulations! You are selected for a free vouchar worth $500") |
|
|
|
interface.launch() |
