Upload 9 files

app.py

@@ -0,0 +1,141 @@
+# Library Load Model
+import pandas as pd
+import numpy as np
+import pickle
+from tensorflow.keras.models import load_model
+import streamlit as st
+# Library Pre-Processing
+import nltk
+import re
+import tensorflow as tf
+from nltk.corpus import stopwords
+from nltk.tokenize import word_tokenize
+from nltk.stem import WordNetLemmatizer
+from tensorflow.keras.preprocessing.text import Tokenizer
+from tensorflow.keras.preprocessing.sequence import pad_sequences
+from gensim.models import Word2Vec
+nltk.download('stopwords')
+
+# # Load tokenizer
+# with open("tokenizer.pkl", "rb") as tokenizer_file:
+#     tokenizer = pickle.load(tokenizer_file)
+# Define the model
+model_path= 'model'
+
+# Load model
+model = tf.keras.models.load_model(model_path)
+
+# Define Stopwords
+## Load Stopwords from NLTK
+from nltk.corpus import stopwords
+stop_words_en = stopwords.words("english")
+
+print('Stopwords from NLTK')
+print(len(stop_words_en), stop_words_en)
+print('')
+
+## Create A New Stopwords
+new_stop_words = ['aye', 'mine', 'have']
+
+# Define Lemmatizer
+lemmatizer = WordNetLemmatizer()
+
+## Merge Stopwords
+stop_words_en = stop_words_en + new_stop_words
+stop_words_en = list(set(stop_words_en))
+print('Out Final Stopwords')
+print(len(stop_words_en), stop_words_en)
+
+# Create A Function for review Preprocessing
+
+def review_preprocessing(review):
+  # Case folding
+    review = review.lower()
+
+  # Mention removal
+    review = re.sub("@[A-Za-z0-9_]+", " ", review)
+
+  # Hashtags removal
+    review = re.sub("#[A-Za-z0-9_]+", " ", review)
+
+  # Newline removal (\n)
+    review = re.sub(r"\\n", " ",review)
+
+  # Whitespace removal
+    review = review.strip()
+
+  # URL removal
+    review = re.sub(r"http\S+", " ", review)
+    review = re.sub(r"www.\S+", " ", review)
+
+  # Non-letter removal (such as emoticon, symbol (like μ, $, 兀), etc
+    review = re.sub("[^A-Za-z\s']", " ", review)
+    review = re.sub("['ï']", " ", review)
+    review = re.sub("['¿']", " ", review)
+    review = re.sub("['½']", " ", review)
+    review = re.sub("['ý']", " ", review)
+  # Tokenization
+    tokens = word_tokenize(review)
+
+  # Stopwords removal
+    tokens = [word for word in tokens if word not in stop_words_en]
+
+  # Lemmetize
+    tokens = [lemmatizer.lemmatize(word) for word in tokens]
+
+  # Combining Tokens
+    review = ' '.join(tokens)
+
+    return review
+
+def preprocess_text(text):
+    '''
+    Function to preprocess text by cleaning, removing stopwords, and lemmatizing.
+
+    Parameters:
+        text (str): The input text to be preprocessed.
+
+    Returns:
+        str: The preprocessed text.
+    '''
+    text = review_preprocessing(text)
+    return text
+
+def run():
+    # membuat title
+    st.title("DETECTION RATING BASED ON MCDONALD'S CUSTOMER REVIEW")
+    st.subheader('Detecting Reviews')
+    st.markdown('---')
+    # Buat form
+    with st.form(key='review'):
+        st.write("## Customers' Review")
+        # URL input
+        text = st.text_input("Enter The Review:")
+        submitted = st.form_submit_button('Predict')
+        # Perform prediction
+        if submitted:
+                df_inf = {'preprocessing_review': text}
+                df_inf = pd.DataFrame([df_inf])
+                # Preprocess the text (apply the same preprocessing steps as used during training)
+                df_inf['preprocessing_review'] = df_inf['preprocessing_review'].apply(lambda x: review_preprocessing(x))
+                # df_inf = model.texts_to_sequences(df_inf)
+                # df_inf = pad_sequences(df_inf, maxlen=700)
+                # Make the prediction using the loaded model
+
+                y_pred_inf = model.predict(df_inf['preprocessing_review'])
+                y_pred_inf = np.argmax(df_inf['preprocessing_review'], axis = -1)
+
+                # Display the prediction result
+                if y_pred_inf == 0:
+                    st.subheader("Prediction: Negative Comment with Rating 1 Star - 2 Stars")
+                elif y_pred_inf == 1:
+                    st.subheader("Prediction: Neutral Comment with Rating 3 Stars")
+                else:
+                    st.subheader("Prediction: Positive Comment with Rating 5 Stars")
+
+                # Display the extracted text
+                st.subheader("Extracted Text:")
+                st.write(text)
+
+if __name__ == '__main__':
+    run()

fingerprint.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a162c26dd698bbbbe98323fa927ad21299bc342c835f02cb8673217029e1c65
+size 54

keras_metadata.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16209a305a20bcf9beaabb389be32cfa6b95e546d5f8ba07180727e7c63031a7
+size 26972

model_inf_Allen_G7.ipynb

@@ -0,0 +1,191 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import pickle\n",
+    "from tensorflow.keras.models import load_model\n",
+    "import tensorflow as tf"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "model_path= 'model'"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "WARNING:tensorflow:From c:\\Users\\user\\anaconda3\\Lib\\site-packages\\keras\\src\\saving\\legacy\\saved_model\\load.py:107: The name tf.gfile.Exists is deprecated. Please use tf.io.gfile.exists instead.\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "model = tf.keras.models.load_model(model_path)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 32,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>reviewer_id</th>\n",
+       "      <th>store_name</th>\n",
+       "      <th>category</th>\n",
+       "      <th>store_address</th>\n",
+       "      <th>latitude</th>\n",
+       "      <th>longitude</th>\n",
+       "      <th>rating_count</th>\n",
+       "      <th>review_time</th>\n",
+       "      <th>review</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>40000</td>\n",
+       "      <td>McDonald's</td>\n",
+       "      <td>Fast food restaurant</td>\n",
+       "      <td>1916 M St NW, Washington, DC 20036, United States</td>\n",
+       "      <td>27.82</td>\n",
+       "      <td>-80.189098</td>\n",
+       "      <td>2.81</td>\n",
+       "      <td>a year ago</td>\n",
+       "      <td>treated badly</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   reviewer_id  store_name              category  \\\n",
+       "0        40000  McDonald's  Fast food restaurant   \n",
+       "\n",
+       "                                       store_address  latitude   longitude  \\\n",
+       "0  1916 M St NW, Washington, DC 20036, United States     27.82  -80.189098   \n",
+       "\n",
+       "   rating_count review_time         review  \n",
+       "0          2.81  a year ago  treated badly  "
+      ]
+     },
+     "execution_count": 32,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Creating new data as prediction\n",
+    "df_inf= {\n",
+    "    'reviewer_id':40000, \n",
+    "    'store_name':\"McDonald's\" , \n",
+    "    'category': 'Fast food restaurant', \n",
+    "    'store_address':'1916 M St NW, Washington, DC 20036, United States',\n",
+    "    'latitude':27.82, \n",
+    "    'longitude':'-80.189098', \n",
+    "    'rating_count': 2.810,\n",
+    "    'review_time':'a year ago', \n",
+    "    'review':'treated badly', \n",
+    "    \n",
+    "    \n",
+    "     \n",
+    "}\n",
+    "df_inf = pd.DataFrame([df_inf])\n",
+    "df_inf"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 35,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import tensorflow as tf\n",
+    "import numpy as np\n",
+    "integer_array = np.array([1, 2, 3], dtype=np.int32)\n",
+    "tensor = tf.convert_to_tensor(integer_array, dtype=tf.float32)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 37,
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "ValueError",
+     "evalue": "Failed to convert a NumPy array to a Tensor (Unsupported object type int).",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[1;31mValueError\u001b[0m                                Traceback (most recent call last)",
+      "Cell \u001b[1;32mIn[37], line 2\u001b[0m\n\u001b[0;32m      1\u001b[0m \u001b[38;5;66;03m# Predict new data visitor\u001b[39;00m\n\u001b[1;32m----> 2\u001b[0m prediction \u001b[38;5;241m=\u001b[39m model\u001b[38;5;241m.\u001b[39mpredict(df_inf)\n\u001b[0;32m      3\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mThis Review Predicted Gave Rating\u001b[39m\u001b[38;5;124m'\u001b[39m, tensor(prediction[\u001b[38;5;241m0\u001b[39m],\u001b[38;5;241m2\u001b[39m))\n",
+      "File \u001b[1;32mc:\\Users\\user\\anaconda3\\Lib\\site-packages\\keras\\src\\utils\\traceback_utils.py:70\u001b[0m, in \u001b[0;36mfilter_traceback.<locals>.error_handler\u001b[1;34m(*args, **kwargs)\u001b[0m\n\u001b[0;32m     67\u001b[0m     filtered_tb \u001b[38;5;241m=\u001b[39m _process_traceback_frames(e\u001b[38;5;241m.\u001b[39m__traceback__)\n\u001b[0;32m     68\u001b[0m     \u001b[38;5;66;03m# To get the full stack trace, call:\u001b[39;00m\n\u001b[0;32m     69\u001b[0m     \u001b[38;5;66;03m# `tf.debugging.disable_traceback_filtering()`\u001b[39;00m\n\u001b[1;32m---> 70\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m e\u001b[38;5;241m.\u001b[39mwith_traceback(filtered_tb) \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[0;32m     71\u001b[0m \u001b[38;5;28;01mfinally\u001b[39;00m:\n\u001b[0;32m     72\u001b[0m     \u001b[38;5;28;01mdel\u001b[39;00m filtered_tb\n",
+      "File \u001b[1;32mc:\\Users\\user\\anaconda3\\Lib\\site-packages\\tensorflow\\python\\framework\\constant_op.py:103\u001b[0m, in \u001b[0;36mconvert_to_eager_tensor\u001b[1;34m(value, ctx, dtype)\u001b[0m\n\u001b[0;32m    101\u001b[0m     dtype \u001b[38;5;241m=\u001b[39m dtypes\u001b[38;5;241m.\u001b[39mas_dtype(dtype)\u001b[38;5;241m.\u001b[39mas_datatype_enum\n\u001b[0;32m    102\u001b[0m ctx\u001b[38;5;241m.\u001b[39mensure_initialized()\n\u001b[1;32m--> 103\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m ops\u001b[38;5;241m.\u001b[39mEagerTensor(value, ctx\u001b[38;5;241m.\u001b[39mdevice_name, dtype)\n",
+      "\u001b[1;31mValueError\u001b[0m: Failed to convert a NumPy array to a Tensor (Unsupported object type int)."
+     ]
+    }
+   ],
+   "source": [
+    "# Predict new data visitor\n",
+    "prediction = model.predict(df_inf)\n",
+    "print('This Review Predicted Gave Rating', tensor(prediction[0],2))"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "base",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.5"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

requirement.txt

@@ -0,0 +1,12 @@
+streamlit
+pandas<2.0.0
+seaborn
+matplotlib
+plotly
+Pillow
+altair
+feature_engine
+scikit-learn==1.2.1
+tensorflow==2.12.0
+nltk
+gensim

saved_model.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef6239b078d76654a3dda616414aada8126a1a76a4f9c2f340a0595621f2c069
+size 3554328