{"cells":[{"metadata":{},"cell_type":"markdown","source":"

RANZCR CLiP. Data Understanding.

\n\n
\n"},{"metadata":{},"cell_type":"markdown","source":"
\n

Quick navigation

\n\n* [1. Basic Data Overview](#1)\n* [2. Image Overview](#2)"},{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true,"_kg_hide-output":true},"cell_type":"code","source":"import numpy as np\nimport pandas as pd\nimport os\n\nimport plotly.express as px\nfrom plotly.subplots import make_subplots\nimport plotly.graph_objs as go\nimport matplotlib.pyplot as plt\nimport cv2","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"\n

1. Basic Data Overview

"},{"metadata":{},"cell_type":"markdown","source":"**train.csv** - contains image IDs, binary labels, and patient IDs.\n\n* StudyInstanceUID - unique ID for each image\n* ETT - Abnormal - endotracheal tube placement abnormal\n* ETT - Borderline - endotracheal tube placement borderline abnormal\n* ETT - Normal - endotracheal tube placement normal\n* NGT - Abnormal - nasogastric tube placement abnormal\n* NGT - Borderline - nasogastric tube placement borderline abnormal\n* NGT - Incompletely Imaged - nasogastric tube placement inconclusive due to imaging\n* NGT - Normal - nasogastric tube placement borderline normal\n* CVC - Abnormal - central venous catheter placement abnormal\n* CVC - Borderline - central venous catheter placement borderline abnormal\n* CVC - Normal - central venous catheter placement normal\n* Swan Ganz Catheter Present\n* PatientID - unique ID for each patient in the dataset"},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"train = pd.read_csv('/kaggle/input/ranzcr-clip-catheter-line-classification/train.csv')\ntrain","execution_count":null,"outputs":[]},{"metadata":{"_kg_hide-input":true,"trusted":true},"cell_type":"code","source":"cols = [\n 'ETT - Abnormal', 'ETT - Borderline', 'ETT - Normal', \n 'NGT - Abnormal', 'NGT - Borderline', 'NGT - Incompletely Imaged', \n 'NGT - Normal', 'CVC - Abnormal', 'CVC - Borderline', \n 'CVC - Normal', 'Swan Ganz Catheter Present'\n]\n\nfig = make_subplots(rows=4, cols=3)\n\ntraces = [\n go.Bar(\n x=[0, 1], \n y=[\n len(train[train[col]==0]),\n len(train[train[col]==1])\n ], \n name=col,\n text = [\n str(round(100 * len(train[train[col]==0]) / len(train), 2)) + '%',\n str(round(100 * len(train[train[col]==1]) / len(train), 2)) + '%'\n ],\n textposition='auto'\n ) for col in cols\n]\n\nfor i in range(len(traces)):\n fig.append_trace(traces[i], (i // 3) + 1, (i % 3) +1)\n\nfig.update_layout(\n title_text='Train columns',\n height=1200,\n width=1000\n)\n\nfig.show()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Let's see how many records for every column in training set have non zero values."},{"metadata":{"_kg_hide-input":true,"trusted":true},"cell_type":"code","source":"x = train[cols].sum(axis=0).sort_values().reset_index()\nx.columns = ['column', 'nonzero_records']\n\nfig = px.bar(\n x, \n x='nonzero_records', \n y='column', \n orientation='h', \n title='Columns and non zero samples', \n height=800, \n width=800\n)\n\nfig.show()","execution_count":null,"outputs":[]},{"metadata":{"_kg_hide-input":true,"trusted":true},"cell_type":"code","source":"data = train[cols].astype(bool).sum(axis=1).reset_index()\ndata.columns = ['row', 'count']\ndata = data.groupby(['count'])['row'].count().reset_index()\n\nfig = px.bar(\n data, \n y=data['row'], \n x=\"count\", \n title='Number of activations for every sample in training set', \n width=800, \n height=500\n)\n\nfig.show()","execution_count":null,"outputs":[]},{"metadata":{"_kg_hide-input":true,"trusted":true},"cell_type":"code","source":"data = train[cols].astype(bool).sum(axis=1).reset_index()\ndata.columns = ['row', 'count']\ndata = data.groupby(['count'])['row'].count().reset_index()\n\nfig = px.pie(\n data, \n values=round((100 * data['row'] / len(train)), 2), \n names=\"count\", \n title='Number of activations for every sample (Percent)', \n width=800, \n height=500\n)\n\nfig.show()","execution_count":null,"outputs":[]},{"metadata":{"_kg_hide-input":true,"trusted":true},"cell_type":"code","source":"data = train[cols]\n\nf = plt.figure(\n figsize=(12, 12)\n)\n\nplt.matshow(\n data.corr(), \n fignum=f.number\n)\n\nplt.xticks(\n range(data.shape[1]), \n data.columns, \n fontsize=13, \n rotation=70\n)\n\nplt.yticks(\n range(data.shape[1]), \n data.columns, \n fontsize=13\n)\n\ncb = plt.colorbar()\n\ncb.ax.tick_params(\n labelsize=13\n)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"\n

2. Image Overview

"},{"metadata":{},"cell_type":"markdown","source":"Let's check some of our randomly selected images."},{"metadata":{"_kg_hide-input":true,"trusted":true},"cell_type":"code","source":"f, plots = plt.subplots(5, 5, sharex='col', sharey='row', figsize=(17, 17))\nsamples = train.sample(n=25, random_state=666)['StudyInstanceUID'].values\n\nfor i in range(25):\n plots[i // 5, i % 5].axis('off')\n image = cv2.imread(os.path.join(\"/kaggle/input/ranzcr-clip-catheter-line-classification/train/\", f\"{samples[i]}.jpg\"))\n image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)\n plots[i // 5, i % 5].imshow(image)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Let's check image shapes for training set"},{"metadata":{"trusted":true},"cell_type":"code","source":"%%time\n\ncheck_dict = dict()\n\nfor filename in os.listdir(\"/kaggle/input/ranzcr-clip-catheter-line-classification/train/\"):\n img = cv2.imread(\"/kaggle/input/ranzcr-clip-catheter-line-classification/train/\" + filename)\n try:\n check_dict[img.shape] += 1\n except:\n check_dict[img.shape] = 1","execution_count":null,"outputs":[]},{"metadata":{"_kg_hide-input":true,"trusted":true},"cell_type":"code","source":"shapes_df = pd.DataFrame(check_dict.items(), columns=['shape', 'count'])\n\nx = shapes_df.sort_values(['count']).reset_index().drop(['index'], axis=1)\nx['shape'] = x['shape'].astype(str)\nx = x.tail(15)\n\nfig = px.bar(\n x, \n x='count', \n y='shape', \n orientation='h', \n title='Top 15 shape by number of samples', \n height=800, \n width=800\n)\n\nfig.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_annotations = pd.read_csv('/kaggle/input/ranzcr-clip-catheter-line-classification/train_annotations.csv')\ntrain_annotations","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import ast\n\ndef plot_annotation():\n sample = train_annotations.sample(n=1)['StudyInstanceUID'].values[0]\n data = train_annotations[train_annotations['StudyInstanceUID'] == sample]['data'].values[0]\n image_path = \"/kaggle/input/ranzcr-clip-catheter-line-classification/train/\" + sample + \".jpg\"\n data = np.array(ast.literal_eval(data))\n plt.figure(figsize=(10, 10))\n image = cv2.imread(image_path)\n image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)\n plt.imshow(image)\n plt.scatter(data[:, 0], data[:, 1])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plot_annotation()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### To be continued"},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]}],"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":4,"nbformat_minor":4}