{"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":"none","dataSources":[{"sourceId":59093,"databundleVersionId":7469972,"sourceType":"competition"}],"dockerImageVersionId":30635,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"## Brain activity notebook series\n\n### [EEGS 10–20 system](https://www.kaggle.com/code/seshurajup/eegs-10-20-system)\nBetter understanding eegs 10-20 system\n### [Missing Eeg_ids Train.csv vs train_eegs [Resolved]](https://www.kaggle.com/code/seshurajup/missing-eeg-ids-in-train-csv-vs-train-eegs-parquet)\nExtra training eggs [Resolved] as we can ignore it\n### [EDA train.csv](https://www.kaggle.com/code/seshurajup/eda-train-csv)\nDetailed analysis of the train.csv\n### [Eegs Pairing Analysis & Features](https://www.kaggle.com/code/seshurajup/eegs-pairing-analysis-features)\nPairing features analysis and build features\n### [Eegs Target Analysis - Correct way to merge target](https://www.kaggle.com/code/seshurajup/eegs-target-analysis-correct-way-to-merge-target)\nHow to choice the target votes for training\n### [Eegs Train Split (CV)](https://www.kaggle.com/seshurajup/eegs-train-splits-cv)\ngenerate better train split without patient_id overlap\n\n#### **Upvote my work if it is useful**","metadata":{}},{"cell_type":"code","source":"import pandas as pd\nimport matplotlib.pyplot as plt\ntrain = pd.read_csv(\"/kaggle/input/hms-harmful-brain-activity-classification/train.csv\")\ntrain['targets'] = train.apply(lambda x: f\"{x['expert_consensus']}-{x['seizure_vote']}-{x['lpd_vote']}-{x['gpd_vote']}-{x['lrda_vote']}-{x['grda_vote']}-{x['other_vote']}\", axis=1)","metadata":{"execution":{"iopub.status.busy":"2024-01-11T21:14:58.550231Z","iopub.execute_input":"2024-01-11T21:14:58.551033Z","iopub.status.idle":"2024-01-11T21:15:03.995968Z","shell.execute_reply.started":"2024-01-11T21:14:58.550967Z","shell.execute_reply":"2024-01-11T21:15:03.994655Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Go through the discussion for better understanding - [Correct way to merge targets](https://www.kaggle.com/competitions/hms-harmful-brain-activity-classification/discussion/467127)\n\n-- **common sequence of all sub-sequences is 40secs-50secs**\n-- target votes are do not changed, so my guess is we can ignore the 0-40secs and 50secs-90secs sequence as it not given any importance to the targets ( as expert decided based on sub-sequence spike )\n\nor 0-40secs, 50secs-90secs is weak labels approach","metadata":{}},{"cell_type":"code","source":"check = train.loc[train[ 'eeg_id' ]==1628180742]\ncheck","metadata":{"execution":{"iopub.status.busy":"2024-01-11T21:15:03.998572Z","iopub.execute_input":"2024-01-11T21:15:03.998951Z","iopub.status.idle":"2024-01-11T21:15:04.033156Z","shell.execute_reply.started":"2024-01-11T21:15:03.998916Z","shell.execute_reply":"2024-01-11T21:15:04.031983Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"![image.png](attachment:19744bcd-57c3-4467-817f-21c778df4086.png)","metadata":{},"attachments":{"19744bcd-57c3-4467-817f-21c778df4086.png":{"image/png":"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"}}},{"cell_type":"code","source":"check['targets'].unique()","metadata":{"execution":{"iopub.status.busy":"2024-01-11T21:15:04.034848Z","iopub.execute_input":"2024-01-11T21:15:04.035188Z","iopub.status.idle":"2024-01-11T21:15:04.047221Z","shell.execute_reply.started":"2024-01-11T21:15:04.035157Z","shell.execute_reply":"2024-01-11T21:15:04.046090Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Majorly 40-50secs is the reason for selecting Seizure, as without 0-40 and 50-90 do not impacted the egg_id=1628180742 target votes\n\n## CV - no patient shared between train and test","metadata":{}},{"cell_type":"code","source":"train","metadata":{"execution":{"iopub.status.busy":"2024-01-11T21:15:04.049104Z","iopub.execute_input":"2024-01-11T21:15:04.049863Z","iopub.status.idle":"2024-01-11T21:15:04.081506Z","shell.execute_reply.started":"2024-01-11T21:15:04.049831Z","shell.execute_reply":"2024-01-11T21:15:04.080276Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"unique_targets_count = dict(train.groupby(['patient_id'])['targets'].nunique().value_counts(dropna=False))\nplt.figure(figsize=(10, 6))\nplt.bar(list(unique_targets_count.keys()), list(unique_targets_count.values()), color='skyblue')\nplt.title('Unique Targets Count per Patient')\nplt.xlabel('Unique Targets Count')\nplt.ylabel('# patient ids')\nplt.xticks(rotation=0)\nplt.tight_layout()\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2024-01-11T21:15:04.084198Z","iopub.execute_input":"2024-01-11T21:15:04.084574Z","iopub.status.idle":"2024-01-11T21:15:04.661952Z","shell.execute_reply.started":"2024-01-11T21:15:04.084542Z","shell.execute_reply":"2024-01-11T21:15:04.660583Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"unique_targets_count = dict(train.groupby(['eeg_id'])['targets'].nunique().value_counts(dropna=False))\nplt.figure(figsize=(10, 6))\nplt.bar(list(unique_targets_count.keys()), list(unique_targets_count.values()), color='skyblue')\nplt.title('Unique Targets Count per EEG ID')\nplt.xlabel('Unique Targets Count')\nplt.ylabel('# EEG ids')\nplt.xticks(rotation=0)\nplt.tight_layout()\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2024-01-11T21:15:04.663694Z","iopub.execute_input":"2024-01-11T21:15:04.664067Z","iopub.status.idle":"2024-01-11T21:15:05.149494Z","shell.execute_reply.started":"2024-01-11T21:15:04.664035Z","shell.execute_reply":"2024-01-11T21:15:05.148305Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"unique_targets_count ","metadata":{"execution":{"iopub.status.busy":"2024-01-11T21:15:05.151563Z","iopub.execute_input":"2024-01-11T21:15:05.152269Z","iopub.status.idle":"2024-01-11T21:15:05.161594Z","shell.execute_reply.started":"2024-01-11T21:15:05.152231Z","shell.execute_reply":"2024-01-11T21:15:05.160279Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"unique_targets_count[1]/sum([v for _,v in unique_targets_count.items()])","metadata":{"execution":{"iopub.status.busy":"2024-01-11T21:15:05.163987Z","iopub.execute_input":"2024-01-11T21:15:05.164544Z","iopub.status.idle":"2024-01-11T21:15:05.175776Z","shell.execute_reply.started":"2024-01-11T21:15:05.164497Z","shell.execute_reply":"2024-01-11T21:15:05.174176Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"unique_targets_count = dict(train.groupby(['spectrogram_id'])['targets'].nunique().value_counts(dropna=False))\nplt.figure(figsize=(10, 6))\nplt.bar(list(unique_targets_count.keys()), list(unique_targets_count.values()), color='skyblue')\nplt.title('Unique Targets Count per Spectrogram ID')\nplt.xlabel('Unique Targets Count')\nplt.ylabel('# Spectrogram ids')\nplt.xticks(rotation=0)\nplt.tight_layout()\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2024-01-11T21:15:05.177850Z","iopub.execute_input":"2024-01-11T21:15:05.178446Z","iopub.status.idle":"2024-01-11T21:15:05.654673Z","shell.execute_reply.started":"2024-01-11T21:15:05.178382Z","shell.execute_reply":"2024-01-11T21:15:05.653202Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import matplotlib.pyplot as plt\nunique_targets_count = train.groupby(['expert_consensus'])['targets'].nunique()\nplt.figure(figsize=(10, 6))\nunique_targets_count.plot(kind='bar', color='skyblue')\nplt.title('Unique Targets Count per Expert Consenus')\nplt.xlabel('Expert Consensus')\nplt.ylabel('Unique Targets Count')\nplt.xticks(rotation=90)\nplt.tight_layout()\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2024-01-11T21:15:49.788120Z","iopub.execute_input":"2024-01-11T21:15:49.788600Z","iopub.status.idle":"2024-01-11T21:15:50.114718Z","shell.execute_reply.started":"2024-01-11T21:15:49.788565Z","shell.execute_reply":"2024-01-11T21:15:50.113502Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## [Aggregating votes of overlapping rows and create a new expert consensus.by @gunesevitan](https://www.kaggle.com/competitions/hms-harmful-brain-activity-classification/discussion/467127#2597589)\n","metadata":{}},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}