{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.14","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":84493,"databundleVersionId":9871156,"sourceType":"competition"}],"dockerImageVersionId":30786,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"# Libraries","metadata":{}},{"cell_type":"code","source":"import pandas as pd\nimport polars as pl\nimport numpy as np\nimport gc\nfrom matplotlib import pyplot as plt\nimport matplotlib.cm as cm\nfrom sklearn.model_selection import StratifiedGroupKFold","metadata":{"execution":{"iopub.status.busy":"2024-10-26T05:13:59.896088Z","iopub.execute_input":"2024-10-26T05:13:59.896555Z","iopub.status.idle":"2024-10-26T05:13:59.903079Z","shell.execute_reply.started":"2024-10-26T05:13:59.896512Z","shell.execute_reply":"2024-10-26T05:13:59.90168Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Configurations","metadata":{}},{"cell_type":"code","source":"class CONFIG:\n    target_col = \"responder_6\"\n    lag_cols_original = [\"date_id\", \"symbol_id\"] + [f\"responder_{idx}\" for idx in range(9)]\n    lag_cols_rename = { f\"responder_{idx}\" : f\"responder_{idx}_lag_1\" for idx in range(9)}\n    valid_ratio = 0.05\n    start_dt = 1100","metadata":{"execution":{"iopub.status.busy":"2024-10-26T05:13:59.906006Z","iopub.execute_input":"2024-10-26T05:13:59.906478Z","iopub.status.idle":"2024-10-26T05:13:59.916032Z","shell.execute_reply.started":"2024-10-26T05:13:59.906421Z","shell.execute_reply":"2024-10-26T05:13:59.914749Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Load training data","metadata":{}},{"cell_type":"code","source":"# Use last 2 parquets\ntrain = pl.scan_parquet(\n    f\"/kaggle/input/jane-street-real-time-market-data-forecasting/train.parquet\"\n).select(\n    pl.int_range(pl.len(), dtype=pl.UInt32).alias(\"id\"),\n    pl.all(),\n).with_columns(\n    (pl.col(CONFIG.target_col)*2).cast(pl.Int32).alias(\"label\"),\n).filter(\n    pl.col(\"date_id\").gt(CONFIG.start_dt)\n)","metadata":{"execution":{"iopub.status.busy":"2024-10-26T05:13:59.917705Z","iopub.execute_input":"2024-10-26T05:13:59.918097Z","iopub.status.idle":"2024-10-26T05:13:59.93317Z","shell.execute_reply.started":"2024-10-26T05:13:59.918049Z","shell.execute_reply":"2024-10-26T05:13:59.931912Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Create Lags data from training data","metadata":{}},{"cell_type":"code","source":"lags = train.select(pl.col(CONFIG.lag_cols_original))\nlags = lags.rename(CONFIG.lag_cols_rename)\nlags = lags.with_columns(\n    date_id = pl.col('date_id') + 1,  # lagged by 1 day\n    )\nlags = lags.group_by([\"date_id\", \"symbol_id\"], maintain_order=True).last()  # pick up last record of previous date\nlags","metadata":{"execution":{"iopub.status.busy":"2024-10-26T05:13:59.934805Z","iopub.execute_input":"2024-10-26T05:13:59.935188Z","iopub.status.idle":"2024-10-26T05:14:00.277076Z","shell.execute_reply.started":"2024-10-26T05:13:59.935137Z","shell.execute_reply":"2024-10-26T05:14:00.275497Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Merge training data and lags data","metadata":{}},{"cell_type":"code","source":"train = train.join(lags, on=[\"date_id\", \"symbol_id\"],  how=\"left\")\ntrain","metadata":{"execution":{"iopub.status.busy":"2024-10-26T05:14:00.280102Z","iopub.execute_input":"2024-10-26T05:14:00.28048Z","iopub.status.idle":"2024-10-26T05:14:00.314096Z","shell.execute_reply.started":"2024-10-26T05:14:00.280435Z","shell.execute_reply":"2024-10-26T05:14:00.312874Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Split training data and validation data","metadata":{}},{"cell_type":"code","source":"len_train   = train.select(pl.col(\"date_id\")).collect().shape[0]\nvalid_records = int(len_train * CONFIG.valid_ratio)\nlen_ofl_mdl = len_train - valid_records\nlast_tr_dt  = train.select(pl.col(\"date_id\")).collect().row(len_ofl_mdl)[0]\n\nprint(f\"\\n len_train = {len_train}\")\nprint(f\"\\n len_ofl_mdl = {len_ofl_mdl}\")\nprint(f\"\\n---> Last offline train date = {last_tr_dt}\\n\")\n\ntraining_data = train.filter(pl.col(\"date_id\").le(last_tr_dt))\nvalidation_data   = train.filter(pl.col(\"date_id\").gt(last_tr_dt))","metadata":{"execution":{"iopub.status.busy":"2024-10-26T05:14:00.315431Z","iopub.execute_input":"2024-10-26T05:14:00.315968Z","iopub.status.idle":"2024-10-26T05:14:06.977788Z","shell.execute_reply.started":"2024-10-26T05:14:00.315905Z","shell.execute_reply":"2024-10-26T05:14:06.97649Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"validation_data","metadata":{"execution":{"iopub.status.busy":"2024-10-26T05:14:06.979216Z","iopub.execute_input":"2024-10-26T05:14:06.979605Z","iopub.status.idle":"2024-10-26T05:14:07.012111Z","shell.execute_reply.started":"2024-10-26T05:14:06.979551Z","shell.execute_reply":"2024-10-26T05:14:07.010818Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Save data as parquets","metadata":{}},{"cell_type":"code","source":"training_data.collect().\\\nwrite_parquet(\n    f\"training.parquet\", partition_by = \"date_id\",\n)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"validation_data.collect().\\\nwrite_parquet(\n    \"validation.parquet\", partition_by = \"date_id\",\n)","metadata":{"trusted":true},"execution_count":null,"outputs":[]}]}