last milestone project bootcamp

.gitattributes

@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+lstm1_model/variables/variables.data-00000-of-00001 filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,11 @@
+import streamlit as st
+import eda
+import prediction
+
+navigation = st.sidebar.selectbox('page : ', ('EDA', 'Sentiment Prediction'))
+
+if navigation == 'EDA':
+    eda.run()
+
+else:
+    prediction.run()

eda.py

@@ -0,0 +1,83 @@
+import streamlit as st
+import pandas as pd
+import seaborn as sns
+import matplotlib.pyplot as plt
+import plotly.express as px
+from PIL import Image
+from wordcloud import WordCloud
+
+
+st.set_page_config(
+    page_title = 'Sentiment Analysis',
+    layout = 'wide',
+    initial_sidebar_state='expanded'
+)
+
+def run():
+
+    # title
+    st.title( 'Sentiment Prediction')
+
+    # sub header
+    st.subheader('Positive, Neutral, Negative')
+
+    # insert image
+    image = Image.open('sensi.jpg')
+    st.image(image, caption='image from AltextSoft, education purpose only')
+
+    # Deskripsi
+    st.write('Exploratory Data from dataset')
+
+    # show data frame
+    st.write('The first 10 Data')
+    df = pd.read_csv('https://raw.githubusercontent.com/mukhlishr/rasyidi/main/tripadvisor_hotel_reviews.csv')
+    st.dataframe(df.head(10))
+
+    # Barplot target columns 
+    st.write('###### Rating ')
+    fig=plt.figure(figsize=(15,5))
+    sns.countplot(x='Rating', data = df)
+    st.pyplot(fig)
+
+
+    def Sentimen(x):
+      if  x<= 5 and x>3:
+        return 'positive'
+      if x== 3:
+        return 'neutral'
+      if x< 3 and x>=1:
+        return 'negative'  
+    # Create column 'sentimen'
+    df['sentimen'] = df['Rating'].apply(Sentimen)
+
+    # Barplot Sentiment 
+    st.write('###### Sentiment of Review ')
+    fig=plt.figure(figsize=(15,5))
+    sns.countplot(x='sentimen', data = df)
+    st.pyplot(fig)
+
+    # Wordcloud
+    st.write('###### Word Cloud ')
+    def show_wordcloud(data, title = None):
+        wordcloud = WordCloud(
+        background_color='black',
+        max_words=200,
+        max_font_size=45, 
+        scale=1,
+        random_state=1
+    ).generate(" ".join(data))
+        fig = plt.figure(1, figsize=(15, 15))
+        plt.axis('off')
+        if title: 
+            fig.suptitle(title, fontsize=20)
+            fig.subplots_adjust(top=2.3)
+
+        st.plt.imshow(wordcloud)
+        st.plt.show()
+
+    # Wordcloud all
+    show_wordcloud(df['Review'].values)
+    
+
+if __name__ == '__main__':
+    run()

lstm1_model/fingerprint.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b7ac22092976fb14c5dc3d4fa9cbff17981090cff4e21c7e7439fa25666bde0
+size 55

lstm1_model/keras_metadata.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84bca81839322d43a3dabdf82a402aec863fb83721b806192b9f525c0db08270
+size 34241

lstm1_model/saved_model.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e190da7671489d29d2f86b59e2ff6f13694cb4584c8cf5a56abcf71489580830
+size 5377771

lstm1_model/variables/variables.data-00000-of-00001

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a8f262655b9256c7021c6f3059b4f0b0647f923f235baf7f60350a80e8765a4
+size 54617086

prediction.py

@@ -0,0 +1,166 @@
+import streamlit as st
+import pandas as pd
+import numpy as np
+import nltk
+import tensorflow as tf
+from nltk.corpus import stopwords
+import re
+from nltk.tokenize import word_tokenize
+from nltk.stem import WordNetLemmatizer
+from keras.models import load_model
+
+
+
+
+# Load model tf fromat.
+new_model = tf.keras.models.load_model('lstm1_model')
+
+
+
+
+def run():
+
+  with st.form(key='Review & Rating'):
+
+      Review = st.text_input('Review your stay', value='')
+      Rating  = st.selectbox('Rate us', (1,2,3,4,5), index=3, help='1 = very bad , 5 = very nice')
+      st.markdown('---')
+           
+      submitted = st.form_submit_button('Predict')
+
+  data_inf = {
+    'Review':Review,
+    'Rating': Rating,
+  }
+
+  data_inf = pd.DataFrame([data_inf])
+
+      
+  # Define Stopwords
+
+  ## Load Stopwords from NLTK
+  nltk.download('stopwords')
+  nltk.download('punkt')
+
+  stw_en = stopwords.words("english")
+
+  ## Create A New Stopwords
+  new_stw = [ 'hotel', 'room','rooms','good','day','resort','night','restaurant','people','time', "n't", 'got' ,
+   'staff',
+   'stay',
+   'location',
+   'service',
+   'stayed',
+   'beach',
+   'breakfast',
+   'clean',
+   'food',
+   'place',
+   'pool',
+   'like',
+   'really',
+   'bed',
+   'area',
+    'bar',
+   'small',
+   'walk',
+   'little',
+   'bathroom',
+   'trip',
+   'floor',
+   'minute',
+   'water',
+   'lot',
+   'great',
+   'nice',
+   'went',
+   'thing',
+   'problem',
+   'want',
+   'drink',
+   'way',
+   'get',
+   'go',
+   'say'
+   ]
+
+  ## Merge Stopwords
+  stw_en = stw_en + new_stw
+  stw_en = list(set(stw_en))
+
+
+  # Membuat Function untuk preprocessing kata dalam dataframe
+
+
+  def text_proses(teks):
+    # Mengubah Teks ke Lowercase
+    teks = teks.lower()
+
+    # Menghilangkan Mention
+    teks = re.sub("@[A-Za-z0-9_]+", " ", teks)
+
+    # Menghilangkan Hashtag
+    teks = re.sub("#[A-Za-z0-9_]+", " ", teks)
+
+    # Menghilangkan \n
+    teks = re.sub(r"\\n", " ",teks)
+
+    # Menghilangkan Whitespace
+    teks = teks.strip()
+
+
+    # Menghilangkan Link
+    teks = re.sub(r"http\S+", " ", teks)
+    teks = re.sub(r"www.\S+", " ", teks)
+
+    # Menghilangkan yang Bukan Huruf seperti Emoji, Simbol Matematika (seperti μ), dst
+    teks = re.sub("[^A-Za-z\s']", " ", teks)
+
+    # Melakukan Tokenisasi
+    tokens = word_tokenize(teks)
+
+    # Menghilangkan Stopwords
+    teks = ' '.join([word for word in tokens if word not in stw_en])
+
+    return teks
+
+  # Function lemmatizer
+  def lemmatize_text(text):
+    sentence = []
+    for word in text.split():
+      lemmatizer = WordNetLemmatizer()
+      sentence.append(lemmatizer.lemmatize(word, 'v'))
+    return ' '.join(sentence)
+
+
+  # Mengaplikasikan Semua Teknik Preprocessing ke dalam Semua Documents
+
+  data_inf['text_processed'] = data_inf['Review'].apply(text_proses)
+  data_inf
+
+  # lemmatize review
+  nltk.download('wordnet')
+  data_inf['text_processed'] = data_inf['text_processed'].apply(lemmatize_text)
+  data_inf
+
+  inf = data_inf['text_processed']
+
+  st.dataframe(inf)
+
+  if submitted:  
+      # Predict using model ann
+      y_pred = new_model.predict(inf)
+      y_pred_conv= np.where(y_pred >= 0.5, 1, 0)
+      y_pred_df = pd.DataFrame(y_pred_conv, columns=['0', '1', '2'])
+      y_pred_final=y_pred_df.idxmax(1).astype(int)
+
+      if y_pred_final.any() == 2:
+            st.write('## Dude, your guest gave Positive feedback')
+      if y_pred_final.any() == 1:
+            st.write('## Dude, your guest gave Neutral feedback')
+      else:
+            st.write('## Attention, your guest gave Negative feedback')
+
+      
+if __name__ == '__main__':
+    run()

requirements.txt

@@ -0,0 +1,12 @@
+# daftar library yang dibutuhkan semua
+streamlit
+tensorflow
+pandas
+seaborn
+matplotlib
+numpy
+scikit-learn==1.2.1
+plotly
+nltk
+keras
+re