{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.12","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"gpu","dataSources":[{"sourceId":4829,"databundleVersionId":44847,"sourceType":"competition"}],"dockerImageVersionId":30587,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"# **DSI206 Final Project**","metadata":{}},{"cell_type":"markdown","source":"**Yelp Restaurant Photo Classification**","metadata":{}},{"cell_type":"markdown","source":"**EfficientNetB7 SCORES:   0.59**","metadata":{}},{"cell_type":"markdown","source":"# **Table of Content**\n* Data loading\n* Data Exploration\n* Data Preparation\n* Model\n* Result and Summary","metadata":{}},{"cell_type":"markdown","source":"\n# **Introduction**\n* จุดมุ่งหมาย: เพื่อศึกษาและลงมือทำการทำ Multi Label Image Classification โดยสร้างโมเดลที่สามารถทำนายlabelsจากรูปภาพได้\n* เราได้เลือกใช้ EfficientNetB7 ในการทำนายเนื่องจากมีจำนวนพารามิเตอร์ที่มากพอที่จะเรียนรู้จากข้อมูลมาก และEfficientNet ถูกออกแบบโดยให้การสเกลที่มีประสิทธิภาพ ทำให้สามารถใช้งานได้กับขนาดของภาพที่แตกต่างกันได้\n\n\n","metadata":{}},{"cell_type":"markdown","source":"**Members** \n1. ธัญญรัตน์       ถิรธนาพรอนันต์              6524650048\n2. กัญญกร         เพ็งบุญ                  6524651053\n3. กัญชพร          ปรากฎผล               6524651160\n4. สิริปรียา          เจริญจิตร               6524651434\n5. หนึ่งฤทัย         ทองนัด                  6524651442\n6. อารดา           จันทร์คำ                 6524651467    ","metadata":{}},{"cell_type":"markdown","source":"# 1.Data loading\n* นำเข้าข้อมูลและแพคเกจ","metadata":{}},{"cell_type":"code","source":"import pandas as pd\nimport numpy as np\n\nfrom tensorflow.keras.preprocessing import image\nfrom tensorflow.keras.applications import EfficientNetB7\nfrom tensorflow.keras.applications.efficientnet import preprocess_input\nfrom tensorflow.keras.models import Model\nfrom tensorflow.keras.layers import Input, Conv2D, Flatten\n\nfrom sklearn.preprocessing import MultiLabelBinarizer\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.multioutput import MultiOutputClassifier\nfrom sklearn.linear_model import LogisticRegression\n# from xgboost import XGBClassifier\nfrom sklearn.metrics import accuracy_score, classification_report\n\nimport os\nimport random\nimport matplotlib.pyplot as plt\nimport plotly\nimport plotly.graph_objs as go\nimport cv2\n\n","metadata":{"execution":{"iopub.status.busy":"2023-11-28T04:19:47.944699Z","iopub.execute_input":"2023-11-28T04:19:47.945420Z","iopub.status.idle":"2023-11-28T04:19:59.362099Z","shell.execute_reply.started":"2023-11-28T04:19:47.945377Z","shell.execute_reply":"2023-11-28T04:19:59.361079Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"%%time\n\n# extract files\n!apt install pigz\n!pigz -dc /kaggle/input/yelp-restaurant-photo-classification/sample_submission.csv.tgz | tar xf -\n!pigz -dc /kaggle/input/yelp-restaurant-photo-classification/test_photo_to_biz.csv.tgz | tar xf -\n!pigz -dc /kaggle/input/yelp-restaurant-photo-classification/test_photos.tgz | tar xf -\n!pigz -dc /kaggle/input/yelp-restaurant-photo-classification/train.csv.tgz | tar xf -\n!pigz -dc /kaggle/input/yelp-restaurant-photo-classification/train_photo_to_biz_ids.csv.tgz | tar xf -\n!pigz -dc /kaggle/input/yelp-restaurant-photo-classification/train_photos.tgz | tar xf -","metadata":{"execution":{"iopub.status.busy":"2023-11-28T04:19:59.364133Z","iopub.execute_input":"2023-11-28T04:19:59.365163Z","iopub.status.idle":"2023-11-28T04:23:38.214644Z","shell.execute_reply.started":"2023-11-28T04:19:59.365127Z","shell.execute_reply":"2023-11-28T04:23:38.213231Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"แสดงตัวอย่างข้อมูลที่โหลดได้","metadata":{}},{"cell_type":"code","source":"# Load training data that maps business ID to labels\ntrain = pd.read_csv('train.csv')\ndisplay(train.head())\nprint('Shape of train data:', train.shape)\nprint('Number of unique businesses:', train.shape[0])","metadata":{"execution":{"iopub.status.busy":"2023-11-28T04:23:38.216254Z","iopub.execute_input":"2023-11-28T04:23:38.216584Z","iopub.status.idle":"2023-11-28T04:23:38.254565Z","shell.execute_reply.started":"2023-11-28T04:23:38.216554Z","shell.execute_reply":"2023-11-28T04:23:38.253642Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Load training data that maps photos to business ID\ntrain_photo_to_id = pd.read_csv('train_photo_to_biz_ids.csv')\ndisplay(train_photo_to_id.head())\nprint('Shape of train_photo_to_id:', train_photo_to_id.shape)\nprint('Number of images in training set:', train_photo_to_id.shape[0])","metadata":{"execution":{"iopub.status.busy":"2023-11-28T04:23:38.257310Z","iopub.execute_input":"2023-11-28T04:23:38.257891Z","iopub.status.idle":"2023-11-28T04:23:38.336746Z","shell.execute_reply.started":"2023-11-28T04:23:38.257857Z","shell.execute_reply":"2023-11-28T04:23:38.335731Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"โหลดข้อมูลจากไฟล์ csv แล้วเก็บไว้ในตัวแปร","metadata":{}},{"cell_type":"code","source":"\ntrain_biz=pd.read_csv('./train_photo_to_biz_ids.csv')\ntest_biz=pd.read_csv('./test_photo_to_biz.csv')\ntrain=pd.read_csv('./train.csv')\nsub=pd.read_csv('./sample_submission.csv')\n\n","metadata":{"execution":{"iopub.status.busy":"2023-11-28T04:23:38.338104Z","iopub.execute_input":"2023-11-28T04:23:38.338410Z","iopub.status.idle":"2023-11-28T04:23:38.808808Z","shell.execute_reply.started":"2023-11-28T04:23:38.338382Z","shell.execute_reply":"2023-11-28T04:23:38.808046Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"แสดงจำนวนรูปภาพทั้งหมดในไดเรกทอรี train_photos และ test_photos","metadata":{}},{"cell_type":"code","source":"\n\ntrain_dir = 'train_photos'\ntrain_imgs = os.listdir(train_dir)\ntrain_imgs = [file for file in train_imgs if not file.startswith('.')]\n\ntest_dir = 'test_photos'\ntest_imgs = os.listdir(test_dir)\ntest_imgs = [file for file in test_imgs if not file.startswith('.')]\n\nprint('Number of training images:', len(train_imgs))\nprint('Number of testing images:', len(test_imgs))\n\n","metadata":{"execution":{"iopub.status.busy":"2023-11-28T04:23:38.810009Z","iopub.execute_input":"2023-11-28T04:23:38.810344Z","iopub.status.idle":"2023-11-28T04:23:39.507151Z","shell.execute_reply.started":"2023-11-28T04:23:38.810313Z","shell.execute_reply":"2023-11-28T04:23:39.506245Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# **2.Data Exploration**","metadata":{}},{"cell_type":"markdown","source":"    Label:    0: good_for_lunch\n\n              1: good_for_dinner\n\n              2: takes_reservations\n\n              3: outdoor_seating\n\n              4: restaurant_is_expensive\n\n              5: has_alcohol\n\n              6: has_table_service\n\n              7: ambience_is_classy\n\n              8: good_for_kids\n","metadata":{}},{"cell_type":"markdown","source":"แสดงรูปเพื่อการสำรวจ\n","metadata":{}},{"cell_type":"code","source":"# Randomly sample 8 images\nimgs_samples = random.sample(train_imgs, 8)\n\n# Plot random sample of 8 images\nplt.figure(figsize=(15, 10))\nfor i in range(len(imgs_samples)):\n    # OpenCV2 reads images in BGR format\n    img = cv2.imread(os.path.join(train_dir, imgs_samples[i]))\n    # Switch color channels to RGB to make compatible with matplotlib imshow func\n    img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)\n    # Grab image's business ID and labels\n    business = train_photo_to_id.loc[train_photo_to_id['photo_id'] == int(imgs_samples[i][:-4]), 'business_id']\n    labels = train.loc[train['business_id'] == business.values[0], 'labels']\n    # Annotate each image with image ID, business ID, and labels\n    title = \"Image ID: \" + imgs_samples[i] + ' Business: ' + str(business.values[0]) + '\\nLabels: ' + ''.join(labels.values)\n    # Plot the image\n    plt.subplot(2, 4, i+1)\n    plt.tight_layout(pad=0.4, w_pad=0.5, h_pad=1.0)\n    plt.imshow(img)\n    plt.axis('off')\n    plt.title(title)\nplt.show()\n","metadata":{"execution":{"iopub.status.busy":"2023-11-28T04:23:39.508279Z","iopub.execute_input":"2023-11-28T04:23:39.508576Z","iopub.status.idle":"2023-11-28T04:23:41.836330Z","shell.execute_reply.started":"2023-11-28T04:23:39.508549Z","shell.execute_reply":"2023-11-28T04:23:41.835214Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# **3.Data Preparation**","metadata":{}},{"cell_type":"markdown","source":"ตรวจสอบรูปภาพซ้ำและทำการgroupby \"business_id\" แล้วเลือกรูปภาพล่าสุดในแต่ละกลุ่ม\nซี่งจำนวน business_id เหลือ 10,000\n","metadata":{}},{"cell_type":"code","source":"\n\n#เนื่องจากมีการอัพโหลดรูปซ้ำเราเลยเลือกมาแค่รูปล่าสุด\ntrain_biz=train_biz.groupby(\"business_id\").last()\nprint(train_biz.head())","metadata":{"execution":{"iopub.status.busy":"2023-11-28T04:23:41.838123Z","iopub.execute_input":"2023-11-28T04:23:41.838925Z","iopub.status.idle":"2023-11-28T04:23:41.860719Z","shell.execute_reply.started":"2023-11-28T04:23:41.838889Z","shell.execute_reply":"2023-11-28T04:23:41.859888Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"เชื่อมตารางของ train และ train_biz โดยใช้\"business_id\"เป็นคีย์","metadata":{}},{"cell_type":"code","source":"#merge \ntrain=train.merge(train_biz,on=\"business_id\")","metadata":{"execution":{"iopub.status.busy":"2023-11-28T04:23:41.861936Z","iopub.execute_input":"2023-11-28T04:23:41.862256Z","iopub.status.idle":"2023-11-28T04:23:42.212380Z","shell.execute_reply.started":"2023-11-28T04:23:41.862228Z","shell.execute_reply":"2023-11-28T04:23:42.211303Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"แปลง labels จากรูปเป็นรายการlist","metadata":{}},{"cell_type":"code","source":"train['labs']=train['labels'].apply(lambda x:str(x).split(' '))","metadata":{"execution":{"iopub.status.busy":"2023-11-28T04:23:42.217655Z","iopub.execute_input":"2023-11-28T04:23:42.218076Z","iopub.status.idle":"2023-11-28T04:23:43.801609Z","shell.execute_reply.started":"2023-11-28T04:23:42.218041Z","shell.execute_reply":"2023-11-28T04:23:43.800785Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"test_bizได้ groupby ตาม\"business_id\" ซึ่งเราจะนำตารางนี้ไปทำนายในขั้นตอนถัดไป","metadata":{}},{"cell_type":"code","source":"#สิ่งที่ต้องpredict\ntest=test_biz.groupby(\"business_id\").last()\ntest","metadata":{"execution":{"iopub.status.busy":"2023-11-28T04:23:43.802620Z","iopub.execute_input":"2023-11-28T04:23:43.802931Z","iopub.status.idle":"2023-11-28T04:23:45.236842Z","shell.execute_reply.started":"2023-11-28T04:23:43.802905Z","shell.execute_reply":"2023-11-28T04:23:45.234721Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# **4.Modeling**","metadata":{}},{"cell_type":"markdown","source":"#  EfficientNetB7 Model","metadata":{}},{"cell_type":"markdown","source":"ทำการ feature extraction จาก pre-trained model EfficientNetB7 ซึ่งได้ดึง features จากรูปภาพและนำไปใช้เป็น input สำหรับโมเดลในการทำนาย","metadata":{}},{"cell_type":"code","source":"#ลองใช้ deep learning เป็น feature extraction\n# https://keras.io/api/applications/ เลือกจากนี้\n\n#เพิ่ม Convolutional Layers เพื่อลดมิติข้อมูลที่ได้จาก feature extraction\nbase_model = EfficientNetB7(weights='imagenet', include_top=False, input_shape=(600, 600, 3))\nn_filters=32\nkernel_size=3\npool_size=2\ninputs = Input(shape=(600, 600, 3))\n# EfficientNetB7 feature extraction\nbase_features = base_model(inputs, training=False)\n\nx = Conv2D(n_filters, kernel_size, activation='relu')(base_features)\nx = Conv2D(n_filters, kernel_size, activation='relu')(x)\nx = Flatten()(x)\n\n#โมเดล model_fet ใช้ในการ extract features จากรูปภาพ\nmodel_fet = Model(inputs, x)\n\n#โหลดและทำการ preprocess รูปภาพเพื่อให้เข้ากับ model\ndef load_and_preprocess_image(file_path):\n    img = image.load_img(file_path, target_size=(600, 600))\n    img_array = image.img_to_array(img)\n    img_array = np.expand_dims(img_array, axis=0)\n    img_array = preprocess_input(img_array)\n    return img_array\n\n#ฟังก์ชันนี้จะส่ง features ออกมาเป็น numpy array ซึ่งสามารถนำไปใช้ในการ train หรือ predict กับโมเดล\ndef extract_features(file_paths):\n    features = []\n   \n    for i,path in enumerate(file_paths):\n        path=\"/kaggle/working/train_photos/\"+ str(path)+\".jpg\"\n        img_array = load_and_preprocess_image(path)\n        feature = model_fet.predict(img_array)\n        feature = np.squeeze(feature)\n        features.append(feature)\n        print(i)\n    return np.array(features)","metadata":{"execution":{"iopub.status.busy":"2023-11-28T04:23:45.238409Z","iopub.execute_input":"2023-11-28T04:23:45.239131Z","iopub.status.idle":"2023-11-28T04:24:10.228552Z","shell.execute_reply.started":"2023-11-28T04:23:45.239089Z","shell.execute_reply":"2023-11-28T04:24:10.227454Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"ใช้ฟังก์ชัน extract_features เพื่อดึง features จากภาพทั้งหมดที่ระบุในคอลัมน์ 'photo_id'","metadata":{}},{"cell_type":"code","source":"%%time\nfeatures = extract_features(train['photo_id'].tolist())","metadata":{"scrolled":true,"execution":{"iopub.status.busy":"2023-11-28T04:24:10.229918Z","iopub.execute_input":"2023-11-28T04:24:10.230256Z","iopub.status.idle":"2023-11-28T04:29:06.811859Z","shell.execute_reply.started":"2023-11-28T04:24:10.230228Z","shell.execute_reply":"2023-11-28T04:29:06.810637Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"แสดงโครงสร้างของโมเดล","metadata":{}},{"cell_type":"code","source":"# Display summary for the feature extraction model\nprint(\"\\nFeature Extraction Model Summary:\")\nmodel_fet.summary()","metadata":{"execution":{"iopub.status.busy":"2023-11-28T04:29:06.813358Z","iopub.execute_input":"2023-11-28T04:29:06.813747Z","iopub.status.idle":"2023-11-28T04:29:06.917698Z","shell.execute_reply.started":"2023-11-28T04:29:06.813711Z","shell.execute_reply":"2023-11-28T04:29:06.916601Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"แปลง multi-labels ในคอลลัมน์ 'labs'ให้เป็นรูปแบบ One-Hot Encoding โดยใช้class MultiLabelBinarizer","metadata":{}},{"cell_type":"code","source":"mlb = MultiLabelBinarizer()\none_hot_labels = mlb.fit_transform(train['labs'])\none_hot_labels=one_hot_labels[:,:-1]","metadata":{"execution":{"iopub.status.busy":"2023-11-28T04:29:06.919010Z","iopub.execute_input":"2023-11-28T04:29:06.919299Z","iopub.status.idle":"2023-11-28T04:29:06.932123Z","shell.execute_reply.started":"2023-11-28T04:29:06.919274Z","shell.execute_reply":"2023-11-28T04:29:06.931226Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"\nClassification Report ที่ได้จากการใช้ Logistic Regression จะแสดงประสิทธิภาพของโมเดลในการทำนายแต่ละ labels \n* มีการวัดค่า Precision, Recall, และ F1-score สำหรับแต่ละlabels","metadata":{}},{"cell_type":"code","source":"%%time\nX_train, X_test, y_train, y_test = train_test_split(features, one_hot_labels, test_size=0.2, random_state=42)# แบ่งข้อมูลไว้สำหรับเทรน 80% และสำหรับ validate 20%\nbase_classifier = LogisticRegression(C=0.001,solver=\"newton-cholesky\")\nclassifier = MultiOutputClassifier(base_classifier)\nclassifier.fit(X_train, y_train)\npredictions = classifier.predict(X_test)\nprint(\"\\nClassification Report:\\n\", classification_report(y_test, predictions))","metadata":{"execution":{"iopub.status.busy":"2023-11-28T04:29:06.933591Z","iopub.execute_input":"2023-11-28T04:29:06.933939Z","iopub.status.idle":"2023-11-28T04:31:10.963042Z","shell.execute_reply.started":"2023-11-28T04:29:06.933914Z","shell.execute_reply":"2023-11-28T04:31:10.961781Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"ใช้ pipeline_predict เพื่อทำนาย labels ของภาพที่มีในชุดทดสอบ ","metadata":{}},{"cell_type":"code","source":"def pipline_predict(photo_id):\n    path=\"/kaggle/working/test_photos/\"+ str(photo_id)+\".jpg\"\n    img = image.load_img(path, target_size=(600, 600))\n    img_array = image.img_to_array(img)\n    img_array = np.expand_dims(img_array, axis=0)\n    img_array = preprocess_input(img_array)\n    feature = model_fet.predict(img_array)\n    feature = np.squeeze(feature)\n    y_pred=classifier.predict([feature])\n    y_pred=np.where(y_pred > 0.5)[1]\n    return ' '.join(map(str, y_pred))\n   ","metadata":{"execution":{"iopub.status.busy":"2023-11-28T04:31:10.965648Z","iopub.execute_input":"2023-11-28T04:31:10.966408Z","iopub.status.idle":"2023-11-28T04:31:10.981124Z","shell.execute_reply.started":"2023-11-28T04:31:10.966362Z","shell.execute_reply":"2023-11-28T04:31:10.980005Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def pipline_predict_proba(photo_id):\n    path=\"/kaggle/working/test_photos/\"+ str(photo_id)+\".jpg\"\n    img = image.load_img(path, target_size=(600, 600))\n    img_array = image.img_to_array(img)\n    img_array = np.expand_dims(img_array, axis=0)\n    img_array = preprocess_input(img_array)\n    feature = model_fet.predict(img_array)\n    feature = np.squeeze(feature)\n    y_pred=classifier.predict_proba([feature])\n    return y_pred","metadata":{"execution":{"iopub.status.busy":"2023-11-28T04:31:10.982906Z","iopub.execute_input":"2023-11-28T04:31:10.984375Z","iopub.status.idle":"2023-11-28T04:31:10.998129Z","shell.execute_reply.started":"2023-11-28T04:31:10.984331Z","shell.execute_reply":"2023-11-28T04:31:10.996958Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"ตัวอย่างการทำนายlabelsของ business_id(405544)","metadata":{}},{"cell_type":"code","source":"pipline_predict(405544)","metadata":{"execution":{"iopub.status.busy":"2023-11-28T04:31:10.999647Z","iopub.execute_input":"2023-11-28T04:31:11.000846Z","iopub.status.idle":"2023-11-28T04:31:11.187701Z","shell.execute_reply.started":"2023-11-28T04:31:11.000806Z","shell.execute_reply":"2023-11-28T04:31:11.186733Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"ทำ reset_index() เพื่อให้ index เดิมถูกเปลี่ยนเป็นคอลัมน์ใหม่","metadata":{}},{"cell_type":"code","source":"test=test.reset_index()","metadata":{"execution":{"iopub.status.busy":"2023-11-28T04:31:11.189322Z","iopub.execute_input":"2023-11-28T04:31:11.189626Z","iopub.status.idle":"2023-11-28T04:31:11.194884Z","shell.execute_reply.started":"2023-11-28T04:31:11.189598Z","shell.execute_reply":"2023-11-28T04:31:11.193936Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"ใช้ np.vectorize เพื่อที่ pipline_predict จะทำงานได้กับทุกๆ สมาชิกใน numpy array ทีละตัว","metadata":{}},{"cell_type":"code","source":"test[\"labels\"]=np.vectorize(pipline_predict)(test[\"photo_id\"])","metadata":{"scrolled":true,"execution":{"iopub.status.idle":"2023-11-28T04:55:36.535963Z","shell.execute_reply.started":"2023-11-28T04:31:11.196311Z","shell.execute_reply":"2023-11-28T04:55:36.534627Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"แสดงภาพตัวอย่างของการทำนาย","metadata":{}},{"cell_type":"code","source":"from IPython.display import display, Image\nimport random \n\n# สุ่มเลือก 3 รูปภาพ\nrandom_photo_ids = random.sample(test['photo_id'].tolist(), 3)\n\n# วนลูปแสดงผลลัพธ์สำหรับทุกรูปภาพที่สุ่มมา\nfor photo_id in random_photo_ids:\n    prediction = pipline_predict(photo_id)\n    prediction_proba = pipline_predict_proba(photo_id)\n    \n    # โหลดรูปภาพ\n    img_path = \"/kaggle/working/test_photos/\" + str(photo_id) + \".jpg\"\n    img = Image(filename=img_path, width=300, height=300)\n    \n    # แสดงรูปภาพ\n    display(img)\n\n    print(\"Photo ID:\", photo_id)\n    print(\"Prediction:\", prediction)\n    print(\"Predicted Probabilities:\")\n    print(prediction_proba)","metadata":{"execution":{"iopub.status.busy":"2023-11-28T04:55:36.537192Z","iopub.execute_input":"2023-11-28T04:55:36.537455Z","iopub.status.idle":"2023-11-28T04:55:37.503457Z","shell.execute_reply.started":"2023-11-28T04:55:36.537431Z","shell.execute_reply":"2023-11-28T04:55:37.502543Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"นำตาราง test บันทึกเป็นไฟล์ CSV ที่ชื่อ 'submission.csv'","metadata":{}},{"cell_type":"code","source":"test[[\"business_id\",\"labels\"]].to_csv('submission.csv',index=False)","metadata":{"execution":{"iopub.status.busy":"2023-11-28T04:55:37.504585Z","iopub.execute_input":"2023-11-28T04:55:37.504891Z","iopub.status.idle":"2023-11-28T04:55:37.538610Z","shell.execute_reply.started":"2023-11-28T04:55:37.504864Z","shell.execute_reply":"2023-11-28T04:55:37.537620Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# **5. Summary**","metadata":{}},{"cell_type":"markdown","source":"**5.1 Model Summary**\n","metadata":{}},{"cell_type":"markdown","source":"* ใช้ EfficientNetB7 ในการทำfeature extractionและใช้ logistic regession ในการทำนาย \n* ใช้ EfficientNetB7 ที่ไม่ต้องเทรนเอา EfficientNetB7 ของตัวที่เป็นpre-trained มาทำนายจากรูปภาพให้กลายเป็นfeatureของรูปภาพ แล้วเอาfeature ขอรูปนั้นมาเข้าlogistic regessionที่เป็น unconditional method\nแล้วลองทำนาย\n* โมเดล EfficientNetB7 สามารถทำค่า mean F1 score ออกมาได้ค่อนข้างสูงและเป็นที่น่าพอใจเป็นอย่างมากจากโมเดลที่ได้ทำทั้ง 3 โมเดล ซึ่งมเดลได้EfficientNetB7 mean F1 score อยู่ที่ 0.58 ซึ่งสูงกว่าโมเดลอื่น เมื่อทำนายแล้วได้ผลลัพธ์(score)ออกมาสูงที่สุด อีกทั้งยังมีค่าความแม่นยำและค่าความครอบคลุมที่สูง\n    \n   \n    \n    ","metadata":{}},{"cell_type":"markdown","source":"**5.2 Project Summary**\n\n* EfficientNetB7 เป็นโมเดล Convolutional Neural Network (CNN) ที่มีโครงสร้างที่ถูกออกแบบมาเพื่อให้มีประสิทธิภาพสูงในการทำนายภาพ โดยเฉพาะในงานที่เกี่ยวข้องกับการจำแนกหมวดหมู่ของภาพ (image classification) ซึ่งการใช้ EfficientNetB7 เป็นโมเดลที่เหมาะสำหรับการแข่งขันนี้\n* หลังจากเราได้ลองเปรียบเทียบจำนวน Parameters ที่โมเดลสร้างขึ้นมานั้นมีจำนวนต่างกันอย่างเห็นได้ชัด \n\n![387476898_675579141039634_6719644901756049661_n.jpg](attachment:217d2bf9-94cb-473d-ad8b-4504a28965e7.jpg)\n\nโดยลำดับที่ 1 คือโมเดล VGG19 , ลำดับที่ 2 คือโมเดล Resnet50 และลำดับที่ 3 คือโมเดล EfficientNetB7  โดยจำนวน Parameters ของโมเดล EfficientNetB7มีจำนวนเยอะกว่าหลายเท่าตัว\nซึ่งจำนวน  Parameters ที่มากกว่าก็จะทำให้โมเดลของเรารับมือกับข้อมูลใหม่ๆได้ดีมากยิ่งขึ้น","metadata":{},"attachments":{"217d2bf9-94cb-473d-ad8b-4504a28965e7.jpg":{"image/jpeg":"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"}}},{"cell_type":"markdown","source":"# สรุป\nเมื่อเทียบทั้ง 3 โมเดลพบว่า EfficientNetB7 สามารถทำนายผลออกมาได้ค่า score submission สูงสุดคือ 0.59 นั่นหมายความว่าโมเดลนี้สามารถทำนาย labels ให้ตรงกับรูปภาพได้ดีมากกว่าอีก 2 โมเดล","metadata":{}},{"cell_type":"markdown","source":"เนื่องจากโมเดลนี้สามารถปรับขนาดสเกลของโมเดล ซึ่งช่วยให้ได้โมเดลที่มีประสิทธิภาพมากขึ้นและจุดเด่นของโมเดลนี้คือมีความละเอียดและประสิทธิภาพสูง ซึ่งเหมาะกับการทำนายข้อมูลที่มีความหลากหลายมากรวมถึงรุปภาพที่มีความซับซ้อน","metadata":{}},{"cell_type":"markdown","source":"# หมายเหตุ\nสามารถดู Notebook ที่เป็นการทำโมเดลอื่นๆได้ที่นี่\n* โมเดล [VGG19](https://www.kaggle.com/code/siripreya/vgg19/edit/run/152563616)\n* โมเดล [Resnet50](https://www.kaggle.com/code/kunyakornpengboon94/resnet50)","metadata":{}},{"cell_type":"markdown","source":"# References:","metadata":{}},{"cell_type":"markdown","source":"* https://www.kaggle.com/code/enerrio/data-exploration-yelp-classification ในส่วนของการแสดงรูป\n","metadata":{}}]}