{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"# **SIIM COVID-19 EDA**","metadata":{}},{"cell_type":"markdown","source":"![header.jpg](attachment:fa8d9899-e4da-40eb-8a35-48d80cee351f.jpg)","metadata":{},"attachments":{"fa8d9899-e4da-40eb-8a35-48d80cee351f.jpg":{"image/jpeg":"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"}}},{"cell_type":"markdown","source":"## Training and Inferance\n- [SIIM COVID-19 Detectron2 Training](https://www.kaggle.com/ammarnassanalhajali/siim-covid-19-detectron2-training)\n- [SIIM COVID-19 Detectron2 Inferance](https://www.kaggle.com/ammarnassanalhajali/siim-covid-19-detectron2-inferance)\n- [COVID-19 Detection YOLOv5 3Classes [Training] ](https://www.kaggle.com/ammarnassanalhajali/covid-19-detection-yolov5-3classes-training)\n- [COVID-19 Detection YOLOv5 3Classes [Inference]](https://www.kaggle.com/ammarnassanalhajali/covid-19-detection-yolov5-3classes-inference)\n- [SIIM-COVID-19 Detection Training Labels (Dataset)](https://www.kaggle.com/ammarnassanalhajali/siimcovid19-detection-training-label)\n\n### Please if this kernel is useful, <font color='red'>please upvote !!</font>","metadata":{}},{"cell_type":"markdown","source":"# Introduction \n\n* Currently, COVID-19 can be diagnosed via polymerase chain reaction to detect genetic material from the virus or chest radiograph. However, it can take a few hours and sometimes days before the molecular test results are back. By contrast, chest radiographs can be obtained in minutes.\n\n* In this competition, we’ll identify and localize COVID-19 abnormalities on chest radiographs. In particular, we'll categorize the radiographs as negative for pneumonia or typical, indeterminate, or atypical for COVID-19. \n\n* In this competition, we hope to develop a model to help radiologists diagnose the millions of COVID-19 patients more confidently and quickly.\n","metadata":{"papermill":{"duration":0.02339,"end_time":"2021-05-18T16:04:45.542342","exception":false,"start_time":"2021-05-18T16:04:45.518952","status":"completed"},"tags":[]}},{"cell_type":"markdown","source":"# Data & Files\n* **Train folder**: The train dataset comprises 6,334 chest scans in DICOM format\n* All images are stored in paths with the form **study**/**series**/**image**\n    * **study**: The study ID here relates directly to the study-level predictions.\n    *  **image**:The image ID is the ID used for image-level predictions.\n* **Test folder**:The hidden test dataset is of roughly the same scale as the training dataset.\n    \n\n* **train_study_level.csv**: The train study-level metadata, with one row for each study, including correct labels.\n* **train_image_level.csv**: The train image-level metadata, with one row for each image, including both correct labels and any bounding boxes in a dictionary format. Some images in both test and train have multiple bounding boxes.\n* **sample_submission.csv**: A sample submission file containing all image- and study-level IDs.\n","metadata":{"papermill":{"duration":0.021682,"end_time":"2021-05-18T16:04:45.587059","exception":false,"start_time":"2021-05-18T16:04:45.565377","status":"completed"},"tags":[]}},{"cell_type":"markdown","source":"\n# Columns\n### train_study_level.csv\n\n* **id**:unique study identifier\n* **Negative for Pneumonia**:1 if the study is negative for pneumonia, 0 otherwise\n* **Typical Appearance**:1 if the study has this appearance, 0 otherwise\n* **Indeterminate Appearance**:1 if the study has this appearance, 0 otherwise\n* **Atypical Appearance**:1 if the study has this appearance, 0 otherwise\n\n\n","metadata":{"papermill":{"duration":0.021904,"end_time":"2021-05-18T16:04:45.631096","exception":false,"start_time":"2021-05-18T16:04:45.609192","status":"completed"},"tags":[]}},{"cell_type":"markdown","source":"1. **Normal chest X-ray(Negative)**. It is not uncommon for the chest X-ray to be normal early in the disease, so a normal X-ray does not rule out infection.\n1. **Typical** findings or findings commonly associated with COVID-19 in the scientific literature (. These include a reticular pattern, ground-glass opacities and consolidations, with rounded morphology and a confluent or patchy multifocal distribution. The distribution is usually bilateral and peripheral, with a predominance in the lower fields . The differential diagnosis includes organising pneumonia, drug toxicity and other causes of acute lung damage. Between the first and third week from the onset of symptoms, typical X-ray findings may progress to diffuse disease. This is related to a severe clinical hypoxaemia situation, and the main differential diagnosis is acute respiratory distress syndrome (ARDS).\n1. **Indeterminate** findings and findings that may present in cases of COVID-19 pneumonia can have other causes. These include consolidations and ground-glass opacities with a unilateral, central or upper-lobe distribution. The differential diagnosis includes other infections and alveolar oedema.\n1. **Atypical** findings, uncommon findings or findings not reported in COVID-19 pneumonia. These include lobar consolidation, lung nodules or masses, miliary pattern, cavitation and pleural effusion, reported in only 3% of patients and more typical of advanced disease.\n","metadata":{}},{"cell_type":"markdown","source":"### train_image_level.csv\n\n* **id**:unique image identifier\n* **boxes**:bounding boxes in easily-readable dictionary format\n* **label**:the correct prediction label for the provided bounding boxes","metadata":{}},{"cell_type":"markdown","source":"# Importing libraries","metadata":{"papermill":{"duration":0.021752,"end_time":"2021-05-18T16:04:45.675559","exception":false,"start_time":"2021-05-18T16:04:45.653807","status":"completed"},"tags":[]}},{"cell_type":"code","source":"!pip install gdcm","metadata":{"_kg_hide-input":true,"_kg_hide-output":true,"papermill":{"duration":10.353037,"end_time":"2021-05-18T16:04:56.051334","exception":false,"start_time":"2021-05-18T16:04:45.698297","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2021-07-03T09:21:05.183428Z","iopub.execute_input":"2021-07-03T09:21:05.18403Z","iopub.status.idle":"2021-07-03T09:21:16.091002Z","shell.execute_reply.started":"2021-07-03T09:21:05.183938Z","shell.execute_reply":"2021-07-03T09:21:16.089642Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import numpy as np \nimport pandas as pd \nfrom pandas import DataFrame\nfrom matplotlib.lines import Line2D\nimport plotly.express as px\nimport seaborn as sns\nimport os\nimport pydicom\nimport glob\nfrom tqdm.notebook import tqdm\nfrom pydicom.pixel_data_handlers.util import apply_voi_lut\nimport matplotlib.pyplot as plt\nfrom skimage import exposure\nimport cv2\nimport warnings\nfrom fastai.vision.all import *\nfrom fastai.medical.imaging import *\nwarnings.filterwarnings('ignore')\n","metadata":{"_kg_hide-input":true,"papermill":{"duration":5.389596,"end_time":"2021-05-18T16:05:01.471186","exception":false,"start_time":"2021-05-18T16:04:56.08159","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2021-07-03T09:21:16.093843Z","iopub.execute_input":"2021-07-03T09:21:16.09528Z","iopub.status.idle":"2021-07-03T09:21:22.08192Z","shell.execute_reply.started":"2021-07-03T09:21:16.09521Z","shell.execute_reply":"2021-07-03T09:21:22.080586Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# let's take trip around data","metadata":{"papermill":{"duration":0.027968,"end_time":"2021-05-18T16:05:01.528139","exception":false,"start_time":"2021-05-18T16:05:01.500171","status":"completed"},"tags":[]}},{"cell_type":"markdown","source":"##  train_study_level.csv","metadata":{"papermill":{"duration":0.029551,"end_time":"2021-05-18T16:05:01.588668","exception":false,"start_time":"2021-05-18T16:05:01.559117","status":"completed"},"tags":[]}},{"cell_type":"code","source":"train_study_df = pd.read_csv('../input/siim-covid19-detection/train_study_level.csv')\ntrain_study_df = train_study_df.rename(columns = {'Negative for Pneumonia': 'Negative', 'Typical Appearance': 'Typical', 'Indeterminate Appearance': 'Indeterminate', 'Atypical Appearance': 'Atypical'}, inplace = False)\ntrain_study_df.head(6)","metadata":{"_kg_hide-input":true,"papermill":{"duration":0.089629,"end_time":"2021-05-18T16:05:01.706949","exception":false,"start_time":"2021-05-18T16:05:01.61732","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2021-07-03T09:21:22.086279Z","iopub.execute_input":"2021-07-03T09:21:22.086853Z","iopub.status.idle":"2021-07-03T09:21:22.149196Z","shell.execute_reply.started":"2021-07-03T09:21:22.086808Z","shell.execute_reply":"2021-07-03T09:21:22.1477Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def bar_plot(df,x,x_title,y,title,colors=None,text=None):\n    fig = px.bar(x=x,\n                 y=y,\n                 text=text,\n                 labels={x: x_title.title()},   \n                 data_frame=df,\n                 color=colors,\n                 barmode='group',\n                 template=\"simple_white\")\n    \n    texts = [df[col].values for col in y]\n    for i, t in enumerate(texts):\n        fig.data[i].text = t\n        fig.data[i].textposition = 'inside'\n        \n    fig['layout'].title=title\n\n    fig.update_layout(title_font_size=19)\n    fig.update_layout(title_font_family='Droid Serif')\n    fig.update_layout(width=800,height=500)\n        \n\n\n    for trace in fig.data:\n        trace.name = trace.name.replace('_',' ').title()\n\n    fig.update_yaxes(tickprefix=\"\", showgrid=True)\n\n    fig.show()","metadata":{"_kg_hide-input":true,"papermill":{"duration":0.045708,"end_time":"2021-05-18T16:05:01.782555","exception":false,"start_time":"2021-05-18T16:05:01.736847","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2021-07-03T09:21:22.151014Z","iopub.execute_input":"2021-07-03T09:21:22.151409Z","iopub.status.idle":"2021-07-03T09:21:22.162388Z","shell.execute_reply.started":"2021-07-03T09:21:22.151375Z","shell.execute_reply":"2021-07-03T09:21:22.161305Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_study_df['label_y'] = 'Negative'\ntrain_study_df.loc[train_study_df['Typical']==1, 'label_y'] = 'Typical'\ntrain_study_df.loc[train_study_df['Indeterminate']==1, 'label_y'] = 'Indeterminate'\ntrain_study_df.loc[train_study_df['Atypical']==1, 'label_y'] = 'Atypical'\n\ntrain_study_df.head(5)","metadata":{"_kg_hide-input":true,"papermill":{"duration":0.064436,"end_time":"2021-05-18T16:05:01.876135","exception":false,"start_time":"2021-05-18T16:05:01.811699","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2021-07-03T09:21:22.165781Z","iopub.execute_input":"2021-07-03T09:21:22.166133Z","iopub.status.idle":"2021-07-03T09:21:22.195652Z","shell.execute_reply.started":"2021-07-03T09:21:22.166079Z","shell.execute_reply":"2021-07-03T09:21:22.194234Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_study_df1=train_study_df.groupby(['label_y']).size().reset_index(name='counts')\ntrain_study_df1\n\nbar_plot(train_study_df1,\n         'label_y',\n         'target',\n         ['counts'],\n         title='Target')","metadata":{"_kg_hide-input":true,"papermill":{"duration":1.443501,"end_time":"2021-05-18T16:05:03.351103","exception":false,"start_time":"2021-05-18T16:05:01.907602","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2021-07-03T09:21:22.200483Z","iopub.execute_input":"2021-07-03T09:21:22.200963Z","iopub.status.idle":"2021-07-03T09:21:23.933559Z","shell.execute_reply.started":"2021-07-03T09:21:22.200923Z","shell.execute_reply":"2021-07-03T09:21:23.932051Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"\n\n## train_image_level.csv","metadata":{"papermill":{"duration":0.030424,"end_time":"2021-05-18T16:05:03.413849","exception":false,"start_time":"2021-05-18T16:05:03.383425","status":"completed"},"tags":[]}},{"cell_type":"code","source":"train_image_df = pd.read_csv('../input/siim-covid19-detection/train_image_level.csv')\ntrain_image_df.head(2)","metadata":{"_kg_hide-input":true,"papermill":{"duration":0.090969,"end_time":"2021-05-18T16:05:03.537484","exception":false,"start_time":"2021-05-18T16:05:03.446515","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2021-07-03T09:21:23.935701Z","iopub.execute_input":"2021-07-03T09:21:23.936219Z","iopub.status.idle":"2021-07-03T09:21:24.01106Z","shell.execute_reply.started":"2021-07-03T09:21:23.936164Z","shell.execute_reply":"2021-07-03T09:21:24.009717Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"in **Label** Column, the format is as follows: `[class ID] [confidence score] [bounding box]`\n\n* **Class ID**: Either opacity or none\n* **Confidence score**: confidence from your neural network model. If none, the confidence is 1.\n* **Bounding box**:typical xmin ymin xmax ymax format. If class ID is none, the bounding box is 1 0 0 1 1.\n\nThe bounding boxes are also provided in easily readable dictionary format in column **boxes**","metadata":{"papermill":{"duration":0.032293,"end_time":"2021-05-18T16:05:03.601349","exception":false,"start_time":"2021-05-18T16:05:03.569056","status":"completed"},"tags":[]}},{"cell_type":"code","source":"train_image_df['class'] = train_image_df.label.apply(lambda x: x.split()[0])\n#train_image_df['class'].hist(FaceColor=\"#0066aa\")\ntrain_study_df2=train_image_df.groupby(['class']).size().reset_index(name='counts')\nbar_plot(train_study_df2,\n         'class',\n         'class',\n         ['counts'],\n         title='Class')","metadata":{"_kg_hide-input":true,"papermill":{"duration":0.229376,"end_time":"2021-05-18T16:05:03.862763","exception":false,"start_time":"2021-05-18T16:05:03.633387","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2021-07-03T09:21:24.012736Z","iopub.execute_input":"2021-07-03T09:21:24.013064Z","iopub.status.idle":"2021-07-03T09:21:24.115385Z","shell.execute_reply.started":"2021-07-03T09:21:24.013033Z","shell.execute_reply":"2021-07-03T09:21:24.113876Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_image_df['x_min'] = train_image_df.label.apply(lambda x: float(x.split()[2]))\ntrain_image_df['y_min'] = train_image_df.label.apply(lambda x: float(x.split()[3]))\ntrain_image_df['x_max'] = train_image_df.label.apply(lambda x: float(x.split()[4]))\ntrain_image_df['y_max'] = train_image_df.label.apply(lambda x: float(x.split()[5]))\ntrain_image_df.head(3).T","metadata":{"_kg_hide-input":true,"papermill":{"duration":0.075934,"end_time":"2021-05-18T16:05:03.971281","exception":false,"start_time":"2021-05-18T16:05:03.895347","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2021-07-03T09:21:24.118779Z","iopub.execute_input":"2021-07-03T09:21:24.119372Z","iopub.status.idle":"2021-07-03T09:21:24.177052Z","shell.execute_reply.started":"2021-07-03T09:21:24.119316Z","shell.execute_reply":"2021-07-03T09:21:24.175854Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_study_df['StudyInstanceUID'] = train_study_df['id'].apply(lambda x: x.replace('_study', ''))\ndel train_study_df['id']\ntrain_image_df = train_image_df.merge(train_study_df, on='StudyInstanceUID')\ntrain_image_df.sample(3).T","metadata":{"papermill":{"duration":0.07941,"end_time":"2021-05-18T16:05:04.172022","exception":false,"start_time":"2021-05-18T16:05:04.092612","status":"completed"},"tags":[],"_kg_hide-input":true,"execution":{"iopub.status.busy":"2021-07-03T09:21:24.178571Z","iopub.execute_input":"2021-07-03T09:21:24.178939Z","iopub.status.idle":"2021-07-03T09:21:24.221145Z","shell.execute_reply.started":"2021-07-03T09:21:24.178904Z","shell.execute_reply":"2021-07-03T09:21:24.21971Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"\ntrain_image_df['integer_label'] = train_image_df['label_y']\ntrain_image_df.head(3).T","metadata":{"execution":{"iopub.status.busy":"2021-07-03T09:21:24.222932Z","iopub.execute_input":"2021-07-03T09:21:24.223422Z","iopub.status.idle":"2021-07-03T09:21:24.243942Z","shell.execute_reply.started":"2021-07-03T09:21:24.223385Z","shell.execute_reply":"2021-07-03T09:21:24.24243Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from sklearn import preprocessing\nle = preprocessing.LabelEncoder()\nle.fit(train_image_df['integer_label'])\ntrain_image_df['integer_label']=le.transform(train_image_df['integer_label'])\ntrain_image_df.head(3).T","metadata":{"execution":{"iopub.status.busy":"2021-07-03T09:21:24.245988Z","iopub.execute_input":"2021-07-03T09:21:24.246476Z","iopub.status.idle":"2021-07-03T09:21:24.27201Z","shell.execute_reply.started":"2021-07-03T09:21:24.246377Z","shell.execute_reply":"2021-07-03T09:21:24.270912Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_image_df['id_image'] = train_image_df['id']\ntrain_image_df['id'] = train_image_df['id'].apply(lambda x: x.replace('_image', ''))\ntrain_image_df.head(3).T","metadata":{"execution":{"iopub.status.busy":"2021-07-03T09:21:24.273763Z","iopub.execute_input":"2021-07-03T09:21:24.274123Z","iopub.status.idle":"2021-07-03T09:21:24.300896Z","shell.execute_reply.started":"2021-07-03T09:21:24.274071Z","shell.execute_reply":"2021-07-03T09:21:24.299403Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_image_df.to_csv(\"train_image_df.csv\")\n","metadata":{"execution":{"iopub.status.busy":"2021-07-03T09:21:24.303014Z","iopub.execute_input":"2021-07-03T09:21:24.303516Z","iopub.status.idle":"2021-07-03T09:21:24.440321Z","shell.execute_reply.started":"2021-07-03T09:21:24.303479Z","shell.execute_reply":"2021-07-03T09:21:24.438867Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Labels distribution ","metadata":{}},{"cell_type":"code","source":"fig, ax = plt.subplots(2,2,figsize=(18,15))\nsns.kdeplot(train_image_df[\"Negative\"], shade=True,ax=ax[0,0],color=\"#00ff00\")\nax[0,0].set_title(\"Negative for Pneumonia Distribution\",font=\"Serif\", fontsize=15)\nax[0,0].set(xlabel=None)\nsns.kdeplot(train_image_df[\"Typical\"], shade=True,ax=ax[0,1],color=\"#4209ff\")\nax[0,1].set_title(\"Typical Appearance Distribution\",font=\"Serif\", fontsize=15)\nax[0,1].set(xlabel=None)\nsns.kdeplot(train_image_df[\"Indeterminate\"], shade=True,ax=ax[1,0],color=\"#f72545\")\nax[1,0].set_title(\"Indeterminate Appearance Distribution\",font=\"Serif\", fontsize=15)\nax[1,0].set(xlabel=None)\nsns.kdeplot(train_image_df[\"Atypical\"], shade=True,ax=ax[1,1],color=\"#FFBA08\")\nax[1,1].set_title(\"Atypical Appearance Distribution\",font=\"Serif\", fontsize=15)\nax[1,1].set(xlabel=None)\nplt.show()","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2021-07-03T09:21:24.442284Z","iopub.execute_input":"2021-07-03T09:21:24.442736Z","iopub.status.idle":"2021-07-03T09:21:25.335364Z","shell.execute_reply.started":"2021-07-03T09:21:24.442699Z","shell.execute_reply":"2021-07-03T09:21:25.334041Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# A look at the images","metadata":{"papermill":{"duration":0.034185,"end_time":"2021-05-18T16:05:04.240371","exception":false,"start_time":"2021-05-18T16:05:04.206186","status":"completed"},"tags":[]}},{"cell_type":"code","source":"def dicom2array(path, voi_lut=True, fix_monochrome=True):\n    dicom = pydicom.read_file(path)\n    # VOI LUT (if available by DICOM device) is used to\n    # transform raw DICOM data to \"human-friendly\" view\n    if voi_lut:\n        data = apply_voi_lut(dicom.pixel_array, dicom)\n    else:\n        data = dicom.pixel_array\n    # depending on this value, X-ray may look inverted - fix that:\n    if fix_monochrome and dicom.PhotometricInterpretation == \"MONOCHROME1\":\n        data = np.amax(data) - data\n    data = data - np.min(data)\n    data = data / np.max(data)\n    data = (data * 255).astype(np.uint8)\n    return data\n        \n    \ndef plot_img(img, size=(5, 5), is_rgb=True, title=\"\", cmap='gray'):\n    plt.figure(figsize=size)\n    plt.imshow(img, cmap=cmap)\n    plt.suptitle(title)\n    plt.show()\n\n\ndef plot_imgs(imgs, cols=4, size=5, is_rgb=True, title=\"\", cmap='gray', img_size=(300,300)):\n    rows = len(imgs)//cols + 1\n    fig = plt.figure(figsize=(cols*size, rows*size))\n    for i, img in enumerate(imgs):\n        if img_size is not None:\n            img = cv2.resize(img, img_size)\n        fig.add_subplot(rows, cols, i+1)\n        plt.imshow(img, cmap=cmap)\n    plt.suptitle(title)\n    plt.show()","metadata":{"_kg_hide-input":true,"papermill":{"duration":0.050442,"end_time":"2021-05-18T16:05:04.324903","exception":false,"start_time":"2021-05-18T16:05:04.274461","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2021-07-03T09:21:25.337181Z","iopub.execute_input":"2021-07-03T09:21:25.337535Z","iopub.status.idle":"2021-07-03T09:21:25.351571Z","shell.execute_reply.started":"2021-07-03T09:21:25.337502Z","shell.execute_reply":"2021-07-03T09:21:25.349666Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"dicom_paths = get_dicom_files('../input/siim-covid19-detection/train')\nimgs = [dicom2array(path) for path in dicom_paths[-4:]]\nplot_imgs(imgs)","metadata":{"_kg_hide-input":true,"papermill":{"duration":34.127274,"end_time":"2021-05-18T16:05:38.486819","exception":false,"start_time":"2021-05-18T16:05:04.359545","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2021-07-03T09:21:25.353417Z","iopub.execute_input":"2021-07-03T09:21:25.353846Z","iopub.status.idle":"2021-07-03T09:21:53.566663Z","shell.execute_reply.started":"2021-07-03T09:21:25.353811Z","shell.execute_reply":"2021-07-03T09:21:53.565041Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_image_df = train_image_df[~train_image_df.boxes.isnull()] \nclass_names = ['Typical', 'Indeterminate', 'Atypical'] # we have 3 positive classes\nunique_classes = np.unique(train_image_df[class_names].values, axis=0)","metadata":{"_kg_hide-input":true,"papermill":{"duration":0.060956,"end_time":"2021-05-18T16:05:38.588986","exception":false,"start_time":"2021-05-18T16:05:38.52803","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2021-07-03T09:21:53.568469Z","iopub.execute_input":"2021-07-03T09:21:53.568902Z","iopub.status.idle":"2021-07-03T09:21:53.59316Z","shell.execute_reply.started":"2021-07-03T09:21:53.56886Z","shell.execute_reply":"2021-07-03T09:21:53.591776Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Plot images with bounding box","metadata":{"papermill":{"duration":0.039524,"end_time":"2021-05-18T16:05:38.66821","exception":false,"start_time":"2021-05-18T16:05:38.628686","status":"completed"},"tags":[]}},{"cell_type":"code","source":"sns.set_context(\"notebook\", font_scale=1.5, rc={\"lines.linewidth\": 2.5})\n\ndef custom_palette(custom_colors):\n    customPalette = sns.set_palette(sns.color_palette(custom_colors))\n    sns.palplot(sns.color_palette(custom_colors),size=0.5)\n    plt.tick_params(axis='both', labelsize=0, length = 0)\n\npalette = [\"#4209ff\",\"#f72545\",\"#FFBA08\"]\ncustom_palette(palette)\n","metadata":{"_kg_hide-input":true,"papermill":{"duration":0.110356,"end_time":"2021-05-18T16:05:38.81928","exception":false,"start_time":"2021-05-18T16:05:38.708924","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2021-07-03T09:21:53.595063Z","iopub.execute_input":"2021-07-03T09:21:53.595603Z","iopub.status.idle":"2021-07-03T09:21:53.675877Z","shell.execute_reply.started":"2021-07-03T09:21:53.595554Z","shell.execute_reply":"2021-07-03T09:21:53.674744Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### <span style=\"color:#4209ff\">Typical Appearance</span>\n### <span style=\"color:#f72545\">Indeterminate Appearance</span>\n### <span style=\"color:#FFBA08\">Atypical Appearance</span>","metadata":{"papermill":{"duration":0.040001,"end_time":"2021-05-18T16:05:38.899715","exception":false,"start_time":"2021-05-18T16:05:38.859714","status":"completed"},"tags":[]}},{"cell_type":"markdown","source":"# All classes","metadata":{"papermill":{"duration":0.041415,"end_time":"2021-05-18T16:05:38.98167","exception":false,"start_time":"2021-05-18T16:05:38.940255","status":"completed"},"tags":[]}},{"cell_type":"code","source":"from glob import glob\nimgs = []\nlabel2color = {\n    '[1, 0, 0]': [66,9,255], # Typical Appearance\n    '[0, 1, 0]': [247,37,69], # Indeterminate Appearance\n    '[0, 0, 1]': [255,186,8], # Atypical Appearance\n}\nthickness = 3\nscale = 6\n\nfor _, row in train_image_df[train_image_df['Negative']==0].iloc[12:20].iterrows():\n    study_id = row['StudyInstanceUID']\n    img_path = glob(f'../input/siim-covid19-detection/train/{study_id}/*/*')[0]\n    img = dicom2array(path=img_path)\n    img = cv2.resize(img, None, fx=1/scale, fy=1/scale)\n    img = np.stack([img, img, img], axis=-1)\n    \n    claz = row[class_names].values\n    color = label2color[str(claz.tolist())]\n\n    bboxes = []\n    bbox = []\n    for i, l in enumerate(row['label'].split(' ')):\n        if (i % 6 == 0) | (i % 6 == 1):\n            continue\n        bbox.append(float(l)/scale)\n        if i % 6 == 5:\n            bboxes.append(bbox)\n            bbox = []    \n    \n    for box in bboxes:\n        img = cv2.rectangle(\n            img,\n            (int(box[0]), int(box[1])),\n            (int(box[2]), int(box[3])),\n            color, thickness\n    )\n    img = cv2.resize(img, (600,600))\n    imgs.append(img)\n    \nplot_imgs(imgs, cmap=None)","metadata":{"_kg_hide-input":true,"papermill":{"duration":4.64424,"end_time":"2021-05-18T16:05:43.667728","exception":false,"start_time":"2021-05-18T16:05:39.023488","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2021-07-03T09:21:53.679544Z","iopub.execute_input":"2021-07-03T09:21:53.679848Z","iopub.status.idle":"2021-07-03T09:21:58.292959Z","shell.execute_reply.started":"2021-07-03T09:21:53.679819Z","shell.execute_reply":"2021-07-03T09:21:58.291983Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"\n# <span style=\"color:#4209ff\">Typical Appearance</span>\n","metadata":{"papermill":{"duration":0.053569,"end_time":"2021-05-18T16:05:43.775982","exception":false,"start_time":"2021-05-18T16:05:43.722413","status":"completed"},"tags":[]}},{"cell_type":"code","source":"imgs = []\n\nfor _, row in train_image_df[train_image_df['Typical'] == 1].iloc[8:12].iterrows():\n    study_id = row['StudyInstanceUID']\n    img_path = glob(f'../input/siim-covid19-detection/train/{study_id}/*/*')[0]\n    img = dicom2array(path=img_path)\n    img = cv2.resize(img, None, fx=1/scale, fy=1/scale)\n    img = np.stack([img, img, img], axis=-1)\n    \n    claz = row[class_names].values\n    color = label2color[str(claz.tolist())]\n\n    bboxes = []\n    bbox = []\n    for i, l in enumerate(row['label'].split(' ')):\n        if (i % 6 == 0) | (i % 6 == 1):\n            continue\n        bbox.append(float(l)/scale)\n        if i % 6 == 5:\n            bboxes.append(bbox)\n            bbox = []    \n    \n    for box in bboxes:\n        img = cv2.rectangle(\n            img,\n            (int(box[0]), int(box[1])),\n            (int(box[2]), int(box[3])),\n            color, thickness\n    )\n    img = cv2.resize(img, (600,600))\n    imgs.append(img)\n    \nplot_imgs(imgs, cmap=None)\n","metadata":{"_kg_hide-input":true,"papermill":{"duration":1.505924,"end_time":"2021-05-18T16:05:45.334845","exception":false,"start_time":"2021-05-18T16:05:43.828921","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2021-07-03T09:21:58.294842Z","iopub.execute_input":"2021-07-03T09:21:58.295492Z","iopub.status.idle":"2021-07-03T09:21:59.839785Z","shell.execute_reply.started":"2021-07-03T09:21:58.295453Z","shell.execute_reply":"2021-07-03T09:21:59.838431Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# <span style=\"color:#f72545\">Indeterminate Appearance</span>","metadata":{"papermill":{"duration":0.059632,"end_time":"2021-05-18T16:05:45.45339","exception":false,"start_time":"2021-05-18T16:05:45.393758","status":"completed"},"tags":[]}},{"cell_type":"code","source":"imgs = []\n\nfor _, row in train_image_df[train_image_df['Indeterminate'] == 1].iloc[2:6].iterrows():\n    study_id = row['StudyInstanceUID']\n    img_path = glob(f'../input/siim-covid19-detection/train/{study_id}/*/*')[0]\n    img = dicom2array(path=img_path)\n    img = cv2.resize(img, None, fx=1/scale, fy=1/scale)\n    img = np.stack([img, img, img], axis=-1)\n    \n    claz = row[class_names].values\n    color = label2color[str(claz.tolist())]\n\n    bboxes = []\n    bbox = []\n    for i, l in enumerate(row['label'].split(' ')):\n        if (i % 6 == 0) | (i % 6 == 1):\n            continue\n        bbox.append(float(l)/scale)\n        if i % 6 == 5:\n            bboxes.append(bbox)\n            bbox = []    \n    \n    for box in bboxes:\n        img = cv2.rectangle(\n            img,\n            (int(box[0]), int(box[1])),\n            (int(box[2]), int(box[3])),\n            color, thickness\n    )\n    img = cv2.resize(img, (600,600))\n    imgs.append(img)\n    \nplot_imgs(imgs, cmap=None)","metadata":{"_kg_hide-input":true,"papermill":{"duration":2.204774,"end_time":"2021-05-18T16:05:47.717166","exception":false,"start_time":"2021-05-18T16:05:45.512392","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2021-07-03T09:21:59.842559Z","iopub.execute_input":"2021-07-03T09:21:59.843047Z","iopub.status.idle":"2021-07-03T09:22:01.975885Z","shell.execute_reply.started":"2021-07-03T09:21:59.843002Z","shell.execute_reply":"2021-07-03T09:22:01.974807Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# <span style=\"color:#FFBA08\">Atypical Appearance</span>","metadata":{"papermill":{"duration":0.065001,"end_time":"2021-05-18T16:05:47.849217","exception":false,"start_time":"2021-05-18T16:05:47.784216","status":"completed"},"tags":[]}},{"cell_type":"code","source":"imgs = []\n\nfor _, row in train_image_df[train_image_df['Atypical'] == 1].iloc[0:4].iterrows():\n    study_id = row['StudyInstanceUID']\n    img_path = glob(f'../input/siim-covid19-detection/train/{study_id}/*/*')[0]\n    img = dicom2array(path=img_path)\n    img = cv2.resize(img, None, fx=1/scale, fy=1/scale)\n    img = np.stack([img, img, img], axis=-1)\n    \n    claz = row[class_names].values\n    color = label2color[str(claz.tolist())]\n\n    bboxes = []\n    bbox = []\n    for i, l in enumerate(row['label'].split(' ')):\n        if (i % 6 == 0) | (i % 6 == 1):\n            continue\n        bbox.append(float(l)/scale)\n        if i % 6 == 5:\n            bboxes.append(bbox)\n            bbox = []    \n    \n    for box in bboxes:\n        img = cv2.rectangle(\n            img,\n            (int(box[0]), int(box[1])),\n            (int(box[2]), int(box[3])),\n            color, thickness\n    )\n    img = cv2.resize(img, (600,600))\n    imgs.append(img)\n    \nplot_imgs(imgs, cmap=None)","metadata":{"_kg_hide-input":true,"papermill":{"duration":2.186093,"end_time":"2021-05-18T16:05:50.099422","exception":false,"start_time":"2021-05-18T16:05:47.913329","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2021-07-03T09:22:01.977617Z","iopub.execute_input":"2021-07-03T09:22:01.977984Z","iopub.status.idle":"2021-07-03T09:22:04.19307Z","shell.execute_reply.started":"2021-07-03T09:22:01.977947Z","shell.execute_reply":"2021-07-03T09:22:04.19164Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# More visualization","metadata":{}},{"cell_type":"code","source":"train_image_df = pd.read_csv('./train_image_df.csv')","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2021-07-03T09:22:04.194484Z","iopub.execute_input":"2021-07-03T09:22:04.194958Z","iopub.status.idle":"2021-07-03T09:22:04.230448Z","shell.execute_reply.started":"2021-07-03T09:22:04.194916Z","shell.execute_reply":"2021-07-03T09:22:04.229643Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_image_df['x_mid'] = train_image_df.apply(lambda row: (row.x_max+row.x_min)/2, axis =1)\ntrain_image_df['y_mid'] = train_image_df.apply(lambda row: (row.y_max+row.y_min)/2, axis =1)\n\ntrain_image_df['w'] = train_image_df.apply(lambda row: (row.x_max-row.x_min), axis =1)\ntrain_image_df['h'] = train_image_df.apply(lambda row: (row.y_max-row.y_min), axis =1)\n\ntrain_image_df['area'] = train_image_df['w']*train_image_df['h']\ntrain_image_df.head()","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2021-07-03T09:22:04.23155Z","iopub.execute_input":"2021-07-03T09:22:04.232016Z","iopub.status.idle":"2021-07-03T09:22:04.945977Z","shell.execute_reply.started":"2021-07-03T09:22:04.231973Z","shell.execute_reply":"2021-07-03T09:22:04.94517Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"features = ['x_min', 'y_min', 'x_max', 'y_max', 'x_mid', 'y_mid', 'w', 'h', 'area']\nX = train_image_df[features]\ny = train_image_df['integer_label']\nX.shape, y.shape","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2021-07-03T09:22:04.947096Z","iopub.execute_input":"2021-07-03T09:22:04.947551Z","iopub.status.idle":"2021-07-03T09:22:04.956377Z","shell.execute_reply.started":"2021-07-03T09:22:04.947509Z","shell.execute_reply":"2021-07-03T09:22:04.95522Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"class_ids, class_names = list(zip(*set(zip(train_image_df.integer_label, train_image_df.label_y))))\nclasses = list(np.array(class_names)[np.argsort(class_ids)])\nclasses = list(map(lambda x: str(x), classes))\nclasses","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2021-07-03T09:22:04.958039Z","iopub.execute_input":"2021-07-03T09:22:04.958638Z","iopub.status.idle":"2021-07-03T09:22:04.975434Z","shell.execute_reply.started":"2021-07-03T09:22:04.9586Z","shell.execute_reply":"2021-07-03T09:22:04.973809Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# t-SNE Visualization\nt-SNE is a tool to visualize high-dimensional data. It converts similarities between data points to joint probabilities and tries to minimize the Kullback-Leibler divergence between the joint probabilities of the low-dimensional embedding and the high-dimensional data. t-SNE has a cost function that is not convex, i.e. with different initializations we can get different results.","metadata":{}},{"cell_type":"code","source":"%%time\nfrom sklearn.manifold import TSNE\n\ntsne = TSNE(n_components = 2, perplexity = 40, random_state=1, n_iter=50000)\ndata_X = X\ndata_y = y.loc[data_X.index]\nembs = tsne.fit_transform(data_X)\n# Add to dataframe for convenience\nplot_x = embs[:, 0]\nplot_y = embs[:, 1]","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2021-07-03T09:22:04.977265Z","iopub.execute_input":"2021-07-03T09:22:04.977844Z","iopub.status.idle":"2021-07-03T09:24:22.888926Z","shell.execute_reply.started":"2021-07-03T09:22:04.977798Z","shell.execute_reply":"2021-07-03T09:24:22.88796Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import matplotlib.pyplot as plt\nplt.figure(figsize = (15, 15))\nplt.axis('off')\nscatter = plt.scatter(plot_x, plot_y, marker = 'o',s = 50, c=data_y.tolist(), alpha= 0.5,cmap='viridis')\nplt.legend(handles=scatter.legend_elements()[0], labels=classes)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2021-07-03T09:24:22.890181Z","iopub.execute_input":"2021-07-03T09:24:22.89065Z","iopub.status.idle":"2021-07-03T09:24:23.218339Z","shell.execute_reply.started":"2021-07-03T09:24:22.890616Z","shell.execute_reply":"2021-07-03T09:24:23.216911Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# BBox Location\n## x_mid Vs y_mid\n","metadata":{}},{"cell_type":"code","source":"from scipy.stats import gaussian_kde\n\n\nx_val = train_image_df.x_mid.values\ny_val = train_image_df.y_mid.values\n\n# Calculate the point density\nxy = np.vstack([x_val,y_val])\nz = gaussian_kde(xy)(xy)\n\nfig, ax = plt.subplots(figsize = (10, 10))\nax.axis('off')\nax.scatter(x_val, y_val, c=z, s=100, cmap='viridis')\n# ax.set_xlabel('x_mid')\n# ax.set_ylabel('y_mid')\nplt.show()","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2021-07-03T09:24:23.219849Z","iopub.execute_input":"2021-07-03T09:24:23.220204Z","iopub.status.idle":"2021-07-03T09:24:24.382965Z","shell.execute_reply.started":"2021-07-03T09:24:23.220169Z","shell.execute_reply":"2021-07-03T09:24:24.381906Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## bbox_w Vs bbox_h\n","metadata":{}},{"cell_type":"code","source":"x_val = train_image_df.w.values\ny_val = train_image_df.h.values\n\n# Calculate the point density\nxy = np.vstack([x_val,y_val])\nz = gaussian_kde(xy)(xy)\n\nfig, ax = plt.subplots(figsize = (10, 10))\nax.axis('off')\nax.scatter(x_val, y_val, c=z, s=100, cmap='viridis')\n# ax.set_xlabel('bbox_width')\n# ax.set_ylabel('bbox_height')\nplt.show()","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2021-07-03T09:24:24.384554Z","iopub.execute_input":"2021-07-03T09:24:24.384904Z","iopub.status.idle":"2021-07-03T09:24:25.568833Z","shell.execute_reply.started":"2021-07-03T09:24:24.384867Z","shell.execute_reply":"2021-07-03T09:24:25.567682Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Image Aspect Ratio","metadata":{}},{"cell_type":"code","source":"\ntrain_image_df1 = pd.read_csv('../input/siim-covid19-resized-1024px/meta.csv')\n\nx_val = train_image_df1.dim0.values\ny_val = train_image_df1.dim1.values\n\n# Calculate the point density\nxy = np.vstack([x_val,y_val])\nz = gaussian_kde(xy)(xy)\n\nfig, ax = plt.subplots(figsize = (10, 10))\nax.axis('off')\nax.scatter(x_val, y_val, c=z, s=100, cmap='viridis')\n# ax.set_xlabel('image_width')\n# ax.set_ylabel('image_height')\nplt.show()","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2021-07-03T09:24:25.573058Z","iopub.execute_input":"2021-07-03T09:24:25.573478Z","iopub.status.idle":"2021-07-03T09:24:27.203998Z","shell.execute_reply.started":"2021-07-03T09:24:25.573441Z","shell.execute_reply":"2021-07-03T09:24:27.202643Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### If you like my work, please upvote","metadata":{}},{"cell_type":"markdown","source":"![download.jpg](attachment:40dd61af-b701-44ab-a881-45d89476dcf6.jpg)","metadata":{"papermill":{"duration":0.070402,"end_time":"2021-05-18T16:05:50.270951","exception":false,"start_time":"2021-05-18T16:05:50.200549","status":"completed"},"tags":[]},"attachments":{"40dd61af-b701-44ab-a881-45d89476dcf6.jpg":{"image/jpeg":"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"}}},{"cell_type":"markdown","source":"# References\n1. https://www.kaggle.com/tanlikesmath/siim-covid-19-detection-a-simple-eda\n1. https://www.kaggle.com/yujiariyasu/plot-3positive-classes\n1. https://www.kaggle.com/ruchi798/siim-covid-19-detection-eda-data-augmentation\n1. Chamorro, E. Martínez, A. Díez Tascón, L. Ibáñez Sanz, S. Ossaba Vélez, and S. Borruel Nacenta. \"Radiologic diagnosis of patients with COVID-19.\" Radiología (English Edi-tion) 63, no. 1 (2021): 56-73.\n","metadata":{"papermill":{"duration":0.072897,"end_time":"2021-05-18T16:05:50.416969","exception":false,"start_time":"2021-05-18T16:05:50.344072","status":"completed"},"tags":[]}}]}