SKRIPSI

import anvil.server anvil.server.connect("6UM23VOV3QVURHBZIP2T34RY-7ONIKWBQIBLJ6MZA")

import requests import anvil.media @anvil.server.callable def get_reviews(appid, params={'json':1}): url = 'https://store.steampowered.com/appreviews/' response = requests.get(url=url+appid, params=params, headers={'User-Agent': 'Mozilla/5.0'}) return response.json()

import pandas as pd import anvil.media df_selected_column = pd.DataFrame() @anvil.server.callable def get_n_reviews(appid, n): global df_selected_column appid = str(appid) reviews = [] cursor = '*' params = { 'json' : 1, 'filter' : 'all', 'language' : 'english', 'day_range' : 9223372036854775807, 'review_type' : 'all', 'purchase_type' : 'all' } while n > 0: params['cursor'] = cursor.encode() params['num_per_page'] = min(100, n) n -= 100 response = get_reviews(appid, params) cursor = response['cursor'] reviews += response['reviews'] if len(response['reviews']) < 100: break df_all_column = pd.json_normalize(reviews, sep='_') df_selected_column = df_all_column[['review','voted_up','votes_up','author_playtime_at_review']]

import matplotlib.pyplot as plt # our main display package import string # used for preprocessing import re # used for preprocessing import nltk # the Natural Language Toolkit, used for preprocessing import numpy as np # used for managing NaNs from nltk.tokenize import word_tokenize from nltk.corpus import stopwords # used for preprocessing from nltk.stem import WordNetLemmatizer # used for preprocessing from sklearn.feature_extraction.text import TfidfVectorizer from sklearn.model_selection import train_test_split # for splitting dataset into training and test from sklearn.preprocessing import MinMaxScaler # for normalizing values from sklearn import svm # Support Vector Machine model from sklearn import metrics #Import scikit-learn metrics module for accuracy calculation from textblob import TextBlob # to determine subjectivity and polarity level nltk.download('stopwords') nltk.download('wordnet') nltk.download('punkt') # remove urls, handles, and the hashtag from hashtags (taken from https://stackoverflow.com/questions/8376691/how-to-remove-hashtag-user-link-of-a-tweet-using-regular-expression) def remove_urls(text): new_text = ' '.join(re.sub("(@[A-Za-z0-9]+)|([^0-9A-Za-z \t])|(\w+:\/\/\S+)"," ",text).split()) return new_text # make all text lowercase def text_lowercase(text): return text.lower() # remove numbers def remove_numbers(text): result = re.sub(r'\d+', '', text) return result # remove punctuation def remove_punctuation(text): translator = str.maketrans('', '', string.punctuation) return text.translate(translator) # tokenize def tokenize(text): text = word_tokenize(text) return text # remove stopwords stop_words = set(stopwords.words('english')) def remove_stopwords(text): text = [i for i in text if not i in stop_words] return text # lemmatize lemmatizer = WordNetLemmatizer() def lemmatize(text): text = [lemmatizer.lemmatize(token) for token in text] return text def preprocessing(text): text = text_lowercase(text) text = remove_urls(text) text = remove_numbers(text) text = remove_punctuation(text) text = tokenize(text) text = remove_stopwords(text) text = lemmatize(text) text = ' '.join(text) return text @anvil.server.callable def process_text(): pp_text_train = [] # kolom teks pre-proses for text_data in df_selected_column['review']: pp_text_data = preprocessing(text_data) pp_text_train.append(pp_text_data) df_selected_column['pp_text'] = pp_text_train # tambahkan kolom teks pre-proses kedalam dataset @anvil.server.callable def polarity(): text_polarity = [] for text_data in df_selected_column['pp_text']: text = TextBlob(text_data).polarity text_polarity.append(text) df_selected_column['polarity'] = text_polarity @anvil.server.callable def subjectivity(): text_subjectivity = [] for text_data in df_selected_column['pp_text']: text = TextBlob(text_data).subjectivity text_subjectivity.append(text) df_selected_column['subjectivity'] = text_subjectivity

scaler = MinMaxScaler() @anvil.server.callable def normalize(): df_selected_column['author_playtime_at_review_normalized'] = scaler.fit_transform(df_selected_column[['author_playtime_at_review']]) df_selected_column['review_votes_up_normalized'] = scaler.fit_transform(df_selected_column[['votes_up']]) df_selected_column['review_length'] = df_selected_column['review'].apply(len) df_selected_column['review_length_normalized'] = scaler.fit_transform(df_selected_column[['review_length']])

from sklearn.feature_extraction.text import TfidfVectorizer from nltk.tokenize import word_tokenize import pickle df_final = pd.DataFrame() @anvil.server.callable def term_weighing(): global df_final token = {} vectorizer = pickle.load(open('tf-idf.pkl','rb')) token = df_selected_column['pp_text'].to_dict() token = list(token.values()) X = vectorizer.transform(token) feature_names = vectorizer.get_feature_names() dense = X.todense() denselist = dense.tolist() dfvectorized = pd.DataFrame(denselist, columns=feature_names) df_final = pd.concat([dfvectorized, df_selected_column.drop(['review', 'voted_up', 'votes_up', 'author_playtime_at_review', 'pp_text', 'review_length'], axis=1)], axis=1, join='inner')

import pickle @anvil.server.callable def classify(): model = pickle.load(open('review_prediction_model.pkl','rb')) prediction = model.predict(df_final) df_selected_column['prediction'] = prediction return df_selected_column.to_dict('records')

@anvil.server.callable def clear_df(): global df_selected_column df_selected_column = df_selected_column.iloc[0:0] global df_final df_final = df_final.iloc[0:0]

# polarity() # subjectivity() # normalize()