Upload app.py

app.py

@@ -0,0 +1,83 @@
+import joblib
+import gradio as gr
+import numpy as np
+import pandas as pd
+import seaborn as sns
+import matplotlib.pyplot as plt
+import warnings, string
+warnings.filterwarnings('ignore')
+from sklearn.model_selection import train_test_split, GridSearchCV
+from sklearn.metrics import classification_report, confusion_matrix, accuracy_score
+import nltk
+from nltk.corpus import stopwords
+from sklearn.feature_extraction.text import CountVectorizer, TfidfTransformer
+from sklearn.naive_bayes import MultinomialNB
+from sklearn.pipeline import Pipeline
+from sklearn.ensemble import RandomForestClassifier
+# from sklearn.tree import DecisionTreeClassifier
+# from sklearn.neighbors import KNeighborsClassifier
+# from sklearn.svm import SVC
+# from sklearn.linear_model import LogisticRegression
+from nltk.corpus import stopwords
+import string, nltk
+from nltk import word_tokenize
+from nltk.stem import PorterStemmer
+from nltk.stem import WordNetLemmatizer
+
+nltk.download('wordnet')
+nltk.download('omw-1.4')
+
+lemmatizer = WordNetLemmatizer()
+stemmer = PorterStemmer()
+
+def clean_text(text):
+    nopunc = [w for w in text if w not in string.punctuation]
+    nopunc = ''.join(nopunc)
+    return  ' '.join([word for word in nopunc.split() if word.lower() not in stopwords.words('english')])
+def preprocess(text):
+    return ' '.join([word for word in word_tokenize(text) if word not in stopwords.words('english') and not word.isdigit() and word not in string.punctuation])
+
+def stem_words(text):
+    return ' '.join([stemmer.stem(word) for word in text.split()])
+
+def lemmatize_words(text):
+    return ' '.join([lemmatizer.lemmatize(word) for word in text.split()])
+
+def text_process(review):
+    nopunc = [char for char in review if char not in string.punctuation]
+    nopunc = ''.join(nopunc)
+    return [word for word in nopunc.split() if word.lower() not in stopwords.words('english')]
+
+
+### IMPORT ML MODEL; best use for multiple reviews involving the same reviewer or user
+print("Running prototype")
+loaded_pipeline = joblib.load("trained_fake_review_detector.pkl")
+print(loaded_pipeline)
+iter_test = ["Hello World"]
+print(loaded_pipeline.predict(iter_test))
+
+initialise_gradio = True
+
+if initialise_gradio:
+    def classify_review(x):
+        iter_x = list(x)
+        result = loaded_pipeline.predict(iter_x)
+
+        return result[0]
+    iface = gr.Interface(fn = classify_review, 
+                        inputs = 'textbox', 
+                        outputs = 'label', 
+                        title = 'Fake Review Detection',
+                        description = 'Input any text that you believe to be fake, this will return an output',
+                        article = 
+                            '''<div>
+                                <p> Hit submit after putting your fake review text to see the results.</p>
+                            </div>''',
+                        share = True)
+
+    #gr.Markdown("## Text Examples")
+
+    # Adding of examples
+    #gr.Examples([["hi", "Adam"], ["hello", "Eve"]], test_fn, cache_examples=True)
+
+    iface.launch(share = True)