{"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":81933,"databundleVersionId":9643020,"sourceType":"competition"}],"dockerImageVersionId":30786,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"# ⚠ Objective ⚠\n

This competition has shown that even slight output variations can significantly impact the score.

\n

Feature engineering with an AutoEncoder particularly tends to cause notable score fluctuations.

\n

Below, methods are outlined for producing consistent outputs by setting seeds.

","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19"}},{"cell_type":"code","source":"import numpy as np\nimport pandas as pd\nimport seaborn as sns\nimport os\nimport re\nfrom sklearn.base import clone\nfrom sklearn.metrics import cohen_kappa_score\nfrom sklearn.model_selection import StratifiedKFold\nfrom scipy.optimize import minimize\nfrom concurrent.futures import ThreadPoolExecutor\nfrom tqdm import tqdm\n\nfrom sklearn.preprocessing import StandardScaler\nimport matplotlib.pyplot as plt\nfrom keras.models import Model\nfrom keras.layers import Input, Dense\nfrom keras.optimizers import Adam\nimport torch\nimport torch.nn as nn\nimport torch.optim as optim\n\nfrom colorama import Fore, Style\nfrom IPython.display import clear_output\nimport warnings\nfrom lightgbm import LGBMRegressor\nfrom xgboost import XGBRegressor\nfrom catboost import CatBoostRegressor\nfrom sklearn.ensemble import VotingRegressor, RandomForestRegressor, GradientBoostingRegressor\nfrom sklearn.impute import SimpleImputer, KNNImputer\nfrom sklearn.pipeline import Pipeline\nwarnings.filterwarnings('ignore')\npd.options.display.max_columns = None\n\nSEED = 42\nn_splits = 5","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def process_file(filename, dirname):\n df = pd.read_parquet(os.path.join(dirname, filename, 'part-0.parquet'))\n df.drop('step', axis=1, inplace=True)\n return df.describe().values.reshape(-1), filename.split('=')[1]\n\ndef load_time_series(dirname) -> pd.DataFrame:\n ids = os.listdir(dirname)\n \n with ThreadPoolExecutor() as executor:\n results = list(tqdm(executor.map(lambda fname: process_file(fname, dirname), ids), total=len(ids)))\n \n stats, indexes = zip(*results)\n \n df = pd.DataFrame(stats, columns=[f\"stat_{i}\" for i in range(len(stats[0]))])\n df['id'] = indexes\n return df\n\n\ntrain = pd.read_csv('/kaggle/input/child-mind-institute-problematic-internet-use/train.csv')\ntest = pd.read_csv('/kaggle/input/child-mind-institute-problematic-internet-use/test.csv')\nsample = pd.read_csv('/kaggle/input/child-mind-institute-problematic-internet-use/sample_submission.csv')\n\ntrain_ts = load_time_series(\"/kaggle/input/child-mind-institute-problematic-internet-use/series_train.parquet\")\ntest_ts = load_time_series(\"/kaggle/input/child-mind-institute-problematic-internet-use/series_test.parquet\")\n\ndf_train = train_ts.drop('id', axis=1)\ndf_test = test_ts.drop('id', axis=1)","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## 🔨 Seed Setting 🔨\n

The random seeds for Python’s standard library, NumPy, and PyTorch are all set to the same value, and random behavior is also controlled if CUDA is enabled

","metadata":{}},{"cell_type":"code","source":"import random\n\ndef set_seed(seed):\n random.seed(seed)\n np.random.seed(seed)\n torch.manual_seed(seed)\n if torch.cuda.is_available():\n torch.cuda.manual_seed(seed)\n torch.cuda.manual_seed_all(seed)\n torch.backends.cudnn.deterministic = True\n torch.backends.cudnn.benchmark = False\n\nset_seed(SEED) ","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"class AutoEncoder(nn.Module):\n def __init__(self, input_dim, encoding_dim):\n super(AutoEncoder, self).__init__()\n self.encoder = nn.Sequential(\n nn.Linear(input_dim, encoding_dim*3),\n nn.ReLU(),\n nn.Linear(encoding_dim*3, encoding_dim*2),\n nn.ReLU(),\n nn.Linear(encoding_dim*2, encoding_dim),\n nn.ReLU()\n )\n self.decoder = nn.Sequential(\n nn.Linear(encoding_dim, input_dim*2),\n nn.ReLU(),\n nn.Linear(input_dim*2, input_dim*3),\n nn.ReLU(),\n nn.Linear(input_dim*3, input_dim),\n nn.Sigmoid()\n )\n \n def forward(self, x):\n encoded = self.encoder(x)\n decoded = self.decoder(encoded)\n return decoded\n\ndef perform_autoencoder(df, encoding_dim=50, epochs=50, batch_size=32):\n scaler = StandardScaler()\n df_scaled = scaler.fit_transform(df)\n \n data_tensor = torch.FloatTensor(df_scaled)\n \n input_dim = data_tensor.shape[1]\n autoencoder = AutoEncoder(input_dim, encoding_dim)\n \n criterion = nn.MSELoss()\n optimizer = optim.Adam(autoencoder.parameters())\n \n for epoch in range(epochs):\n for i in range(0, len(data_tensor), batch_size):\n batch = data_tensor[i : i + batch_size]\n optimizer.zero_grad()\n reconstructed = autoencoder(batch)\n loss = criterion(reconstructed, batch)\n loss.backward()\n optimizer.step()\n \n if (epoch + 1) % 10 == 0:\n print(f'Epoch [{epoch + 1}/{epochs}], Loss: {loss.item():.4f}]')\n \n with torch.no_grad():\n encoded_data = autoencoder.encoder(data_tensor).numpy()\n \n df_encoded = pd.DataFrame(encoded_data, columns=[f'Enc_{i + 1}' for i in range(encoded_data.shape[1])])\n \n return df_encoded","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"encoding_DIM = 60\ntrain_ts_encoded = perform_autoencoder(df_train, encoding_dim=encoding_DIM, epochs=100, batch_size=32)\ntest_ts_encoded = perform_autoencoder(df_test, encoding_dim=encoding_DIM, epochs=100, batch_size=32)\n\n#time series\ntime_series_cols = train_ts_encoded.columns.tolist()\ntrain_ts_encoded[\"id\"]=train_ts[\"id\"]\n\ntrain = pd.merge(train, train_ts_encoded, how=\"left\", on='id')","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"

This training data will give the same result no matter how many times the calculation is performed.
\nThis allows us to reproduce a constant SCORE.

\n\n

Thanks for reading. 👋

","metadata":{}},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}