{"nbformat":4,"nbformat_minor":0,"metadata":{"colab":{"provenance":[],"authorship_tag":"ABX9TyO5J/RoFrpl8dZBuNzBEwXn"},"kernelspec":{"name":"python3","display_name":"Python 3"},"language_info":{"name":"python"}},"cells":[{"cell_type":"code","source":["!pip install -q lightgbm tsfresh optuna scikit-learn pandas numpy matplotlib seaborn joblib"],"metadata":{"id":"wHEiah4us0eh","executionInfo":{"status":"ok","timestamp":1759609790439,"user_tz":-60,"elapsed":9712,"user":{"displayName":"Edmilson Alexandre","userId":"05182212798533402489"}},"colab":{"base_uri":"https://localhost:8080/"},"outputId":"b24f02b2-de03-4178-aa06-6dfdae9e2094"},"execution_count":2,"outputs":[{"output_type":"stream","name":"stdout","text":["\u001b[?25l   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m0.0/400.9 kB\u001b[0m \u001b[31m?\u001b[0m eta \u001b[36m-:--:--\u001b[0m\r\u001b[2K   \u001b[91m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[91m╸\u001b[0m\u001b[90m━━━━━\u001b[0m \u001b[32m348.2/400.9 kB\u001b[0m \u001b[31m10.4 MB/s\u001b[0m eta \u001b[36m0:00:01\u001b[0m\r\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m400.9/400.9 kB\u001b[0m \u001b[31m8.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25h"]}]},{"cell_type":"code","source":["import os\n","import numpy\n","import pandas\n","import joblib\n","import optuna\n","import tsfresh\n","import sklearn\n","import seaborn\n","import lightgbm\n","import matplotlib\n","from google.colab import drive\n","\n","\n","def EDA(file):\n","  pandas.set_option('display.max_columns', 200)\n","  target_col = 'target'\n","  print(\"Shape from file: \", file.shape)\n","  # display(file.head())\n","  # print(file.dtypes)\n","\n","def PipelineCreation(file, target_col):\n","  from sklearn.model_selection import train_test_split\n","  from sklearn.pipeline import Pipeline\n","  from sklearn.impute import SimpleImputer\n","  from sklearn.preprocessing import OneHotEncoder\n","  from sklearn.compose import ColumnTransformer\n","\n","  id_cols = [c for c in ['id', 'time', 'index'] if c in file.columns]\n","  x = file.drop(columns=[target_col] + id_cols, errors='ignore')\n","  y = file[target_col]\n","\n","  numeric_features = x.select_dtypes(include=['number']).columns.tolist()\n","  categorical_features = x.select_dtypes(include=['object', 'category', 'bool']).columns.tolist()\n","  # print(\"Numeric: \", len(numeric_features))\n","  # print(\"Categorical: \", len(categorical_features))\n","  # print(\"X: \", x)\n","  # print(\"Y: \", y)\n","\n","  numeric_transformer = Pipeline([('imputer', SimpleImputer(strategy='median')),])\n","\n","  categorical_transformer = Pipeline([('imputer', SimpleImputer(strategy='most_frequent')),\n","                                      ('ohe', OneHotEncoder(handle_unknown='ignore')),])\n","  print(f\"Num:{len(numeric_features)}\")\n","  preprocessor = ColumnTransformer([\n","      ('num', numeric_transformer, numeric_features),\n","      ('cat', categorical_transformer, categorical_features),\n","  ], remainder='drop')\n","  return x, y, preprocessor\n","\n","def Training(x_train_tr, y_train):\n","  from lightgbm import LGBMClassifier\n","  scale_pos_weight = (y_train==0).sum() / max(1, (y_train==1).sum())\n","  model = LGBMClassifier(\n","      objective='binary',\n","      n_estimators=10000,\n","      learning_rate=0.05,\n","      num_leaves=31,\n","      random_state=42,\n","      scale_pos_weight=scale_pos_weight\n","  )\n","  model.fit(\n","      x_train_tr, y_train,\n","      eval_set=[(x_val_tr, y_val)],\n","      eval_metric='auc',\n","      #my version does not support that method. I need to use callbacks\n","      #early_stopping_rounds=100,\n","      #callbacks=[early_stopping(100), log_evaluation(100)]\n","  )\n","  print(\"Best iteration:\", model.best_iteration_)\n","  print(\"Train AUC:\", model.best_score_['training']['auc'])\n","  print(\"Valid AUC:\", model.best_score_['valid_0']['auc'])\n","\n","  return model\n","\n","\n","\n","from sklearn.model_selection import train_test_split\n","if os.path.exists('/content/drive') == 0:\n","  drive.mount('/content/drive')\n","\n","labels = pandas.read_csv('/content/drive/MyDrive/AI_assets/labels.csv')\n","light_curves  = pandas.read_csv('/content/drive/MyDrive/AI_assets/light_curves.csv')\n","metadata = pandas.read_csv('/content/drive/MyDrive/AI_assets/metadata.csv')\n","data = pandas.read_csv('/content/drive/MyDrive/data2.csv')\n","\n","# im gonna change this under cause i nedd more classes. Using binary interpretation insted of 'CONFIRMED' will help a lot\n","#x, y, preprocessor = PipelineCreation(data, target_col='kepoi_name')\n","\n","data['target'] = data['koi_disposition'].map(\n","    lambda v: 1 if v == \"CONFIRMED\" else 0\n",")\n","\n","x, y, preprocessor = PipelineCreation(data, target_col='target')\n","print(\"First step done. 1 -> PIPELINE CREATION\")\n","# print(\"X: \", x)\n","# print(\"Y: \", y)\n","x_train, x_val, y_train, y_val = train_test_split(\n","    x, y, test_size=0.20, stratify=y, random_state=42\n"," )\n","preprocessor.fit(x_train)\n","x_train_tr = preprocessor.transform(x_train)\n","x_val_tr = preprocessor.transform(x_val)\n","EDA(labels)\n","\n","#debug purposes\n","print(\"Second step done. 2 -> EDA DONE\")\n","print(\"X_train shape:\", x_train_tr.shape)\n","print(\"X_val shape:\", x_val_tr.shape)\n","print(\"y_train distribution:\\n\", y_train.value_counts())\n","print(\"y_val distribution:\\n\", y_val.value_counts())\n","print(\"Check for NaNs:\", x_train_tr.isna().sum().sum(), \"in train,\", x_val_tr.isna().sum().sum(), \"in val\")\n","\n","\n","#model = Training(x_train_tr, y_train)\n","#print(\"Finished Training. 3!!\")\n","\n","\n","# A litle degub made by GPT\n","# print(\"Best iteration:\", model.best_iteration_)\n","# print(\"Train AUC:\", model.best_score_['training']['auc'])\n","# print(\"Valid AUC:\", model.best_score_['valid_0']['auc'])\n"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":873},"id":"-kgzOBe6QXbJ","executionInfo":{"status":"error","timestamp":1759611069253,"user_tz":-60,"elapsed":20,"user":{"displayName":"Edmilson Alexandre","userId":"05182212798533402489"}},"outputId":"98dc3b31-acee-4a6d-c30e-9f15901a1b25"},"execution_count":8,"outputs":[{"output_type":"stream","name":"stdout","text":["Num:133\n","First step done. 1 -> PIPELINE CREATION\n","Shape from file:  (4, 2)\n","Second step done. 2 -> EDA DONE\n","X_train shape: (8, 172)\n","X_val shape: (2, 172)\n","y_train distribution:\n"," target\n","1    6\n","0    2\n","Name: count, dtype: int64\n","y_val distribution:\n"," target\n","0    1\n","1    1\n","Name: count, dtype: int64\n"]},{"output_type":"stream","name":"stderr","text":["/usr/local/lib/python3.12/dist-packages/sklearn/impute/_base.py:635: UserWarning: Skipping features without any observed values: ['koi_gmag_err' 'koi_rmag_err' 'koi_imag_err' 'koi_zmag_err'\n"," 'koi_kepmag_err' 'koi_model_dof' 'koi_model_chisq' 'koi_eccen_err1'\n"," 'koi_eccen_err2' 'koi_longp' 'koi_longp_err1' 'koi_longp_err2'\n"," 'koi_sma_err1' 'koi_sma_err2' 'koi_ingress' 'koi_ingress_err1'\n"," 'koi_ingress_err2' 'koi_incl_err1' 'koi_incl_err2' 'koi_teq_err1'\n"," 'koi_teq_err2' 'koi_sage' 'koi_sage_err1' 'koi_sage_err2']. At least one non-missing value is needed for imputation with strategy='median'.\n","  warnings.warn(\n","/usr/local/lib/python3.12/dist-packages/sklearn/impute/_base.py:635: UserWarning: Skipping features without any observed values: ['koi_gmag_err' 'koi_rmag_err' 'koi_imag_err' 'koi_zmag_err'\n"," 'koi_kepmag_err' 'koi_model_dof' 'koi_model_chisq' 'koi_eccen_err1'\n"," 'koi_eccen_err2' 'koi_longp' 'koi_longp_err1' 'koi_longp_err2'\n"," 'koi_sma_err1' 'koi_sma_err2' 'koi_ingress' 'koi_ingress_err1'\n"," 'koi_ingress_err2' 'koi_incl_err1' 'koi_incl_err2' 'koi_teq_err1'\n"," 'koi_teq_err2' 'koi_sage' 'koi_sage_err1' 'koi_sage_err2']. At least one non-missing value is needed for imputation with strategy='median'.\n","  warnings.warn(\n","/usr/local/lib/python3.12/dist-packages/sklearn/impute/_base.py:635: UserWarning: Skipping features without any observed values: ['koi_gmag_err' 'koi_rmag_err' 'koi_imag_err' 'koi_zmag_err'\n"," 'koi_kepmag_err' 'koi_model_dof' 'koi_model_chisq' 'koi_eccen_err1'\n"," 'koi_eccen_err2' 'koi_longp' 'koi_longp_err1' 'koi_longp_err2'\n"," 'koi_sma_err1' 'koi_sma_err2' 'koi_ingress' 'koi_ingress_err1'\n"," 'koi_ingress_err2' 'koi_incl_err1' 'koi_incl_err2' 'koi_teq_err1'\n"," 'koi_teq_err2' 'koi_sage' 'koi_sage_err1' 'koi_sage_err2']. At least one non-missing value is needed for imputation with strategy='median'.\n","  warnings.warn(\n"]},{"output_type":"error","ename":"AttributeError","evalue":"'numpy.ndarray' object has no attribute 'isna'","traceback":["\u001b[0;31m---------------------------------------------------------------------------\u001b[0m","\u001b[0;31mAttributeError\u001b[0m                            Traceback (most recent call last)","\u001b[0;32m/tmp/ipython-input-2064020500.py\u001b[0m in \u001b[0;36m<cell line: 0>\u001b[0;34m()\u001b[0m\n\u001b[1;32m    109\u001b[0m \u001b[0mprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"y_train distribution:\\n\"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0my_train\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mvalue_counts\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    110\u001b[0m \u001b[0mprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"y_val distribution:\\n\"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0my_val\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mvalue_counts\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 111\u001b[0;31m \u001b[0mprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"Check for NaNs:\"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mx_train_tr\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0misna\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msum\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msum\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m\"in train,\"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mx_val_tr\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0misna\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msum\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msum\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m\"in val\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    112\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    113\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;31mAttributeError\u001b[0m: 'numpy.ndarray' object has no attribute 'isna'"]}]},{"cell_type":"code","source":[],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"CAErcbk0yL-d","executionInfo":{"status":"ok","timestamp":1759540476879,"user_tz":-60,"elapsed":10596,"user":{"displayName":"Edmilson Alexandre","userId":"05182212798533402489"}},"outputId":"571ef5ef-7d8f-462c-8449-2d4444e39ed6"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stdout","text":["Collecting tabgan==1.3.3\n","  Downloading tabgan-1.3.3-py2.py3-none-any.whl.metadata (10.0 kB)\n","Requirement already satisfied: pandas in /usr/local/lib/python3.12/dist-packages (from tabgan==1.3.3) (2.2.2)\n","Requirement already satisfied: numpy in /usr/local/lib/python3.12/dist-packages (from tabgan==1.3.3) (2.0.2)\n","Collecting category-encoders (from tabgan==1.3.3)\n","  Downloading category_encoders-2.8.1-py3-none-any.whl.metadata (7.9 kB)\n","Requirement already satisfied: torch>=1.0 in /usr/local/lib/python3.12/dist-packages (from tabgan==1.3.3) (2.8.0+cu126)\n","Requirement already satisfied: lightgbm>=2.2.3 in /usr/local/lib/python3.12/dist-packages (from tabgan==1.3.3) (4.6.0)\n","Requirement already satisfied: scikit-learn>=1.0.2 in /usr/local/lib/python3.12/dist-packages (from tabgan==1.3.3) (1.6.1)\n","Requirement already satisfied: torchvision in /usr/local/lib/python3.12/dist-packages (from tabgan==1.3.3) (0.23.0+cu126)\n","Requirement already satisfied: python-dateutil in /usr/local/lib/python3.12/dist-packages (from tabgan==1.3.3) (2.9.0.post0)\n","Requirement already satisfied: tqdm in /usr/local/lib/python3.12/dist-packages (from tabgan==1.3.3) (4.67.1)\n","Requirement already satisfied: scipy in /usr/local/lib/python3.12/dist-packages (from lightgbm>=2.2.3->tabgan==1.3.3) (1.16.2)\n","Requirement already satisfied: joblib>=1.2.0 in /usr/local/lib/python3.12/dist-packages (from scikit-learn>=1.0.2->tabgan==1.3.3) (1.5.2)\n","Requirement already satisfied: threadpoolctl>=3.1.0 in /usr/local/lib/python3.12/dist-packages (from scikit-learn>=1.0.2->tabgan==1.3.3) (3.6.0)\n","Requirement already satisfied: filelock in /usr/local/lib/python3.12/dist-packages (from torch>=1.0->tabgan==1.3.3) (3.19.1)\n","Requirement already satisfied: typing-extensions>=4.10.0 in /usr/local/lib/python3.12/dist-packages (from torch>=1.0->tabgan==1.3.3) (4.15.0)\n","Requirement already satisfied: setuptools in /usr/local/lib/python3.12/dist-packages (from torch>=1.0->tabgan==1.3.3) (75.2.0)\n","Requirement already satisfied: sympy>=1.13.3 in /usr/local/lib/python3.12/dist-packages (from torch>=1.0->tabgan==1.3.3) (1.13.3)\n","Requirement already satisfied: networkx in /usr/local/lib/python3.12/dist-packages (from torch>=1.0->tabgan==1.3.3) (3.5)\n","Requirement already satisfied: jinja2 in /usr/local/lib/python3.12/dist-packages (from torch>=1.0->tabgan==1.3.3) (3.1.6)\n","Requirement already satisfied: fsspec in /usr/local/lib/python3.12/dist-packages (from torch>=1.0->tabgan==1.3.3) (2025.3.0)\n","Requirement already satisfied: nvidia-cuda-nvrtc-cu12==12.6.77 in /usr/local/lib/python3.12/dist-packages (from torch>=1.0->tabgan==1.3.3) (12.6.77)\n","Requirement already satisfied: nvidia-cuda-runtime-cu12==12.6.77 in /usr/local/lib/python3.12/dist-packages (from torch>=1.0->tabgan==1.3.3) (12.6.77)\n","Requirement already satisfied: nvidia-cuda-cupti-cu12==12.6.80 in /usr/local/lib/python3.12/dist-packages (from torch>=1.0->tabgan==1.3.3) (12.6.80)\n","Requirement already satisfied: nvidia-cudnn-cu12==9.10.2.21 in /usr/local/lib/python3.12/dist-packages (from torch>=1.0->tabgan==1.3.3) (9.10.2.21)\n","Requirement already satisfied: nvidia-cublas-cu12==12.6.4.1 in /usr/local/lib/python3.12/dist-packages (from torch>=1.0->tabgan==1.3.3) (12.6.4.1)\n","Requirement already satisfied: nvidia-cufft-cu12==11.3.0.4 in /usr/local/lib/python3.12/dist-packages (from torch>=1.0->tabgan==1.3.3) (11.3.0.4)\n","Requirement already satisfied: nvidia-curand-cu12==10.3.7.77 in /usr/local/lib/python3.12/dist-packages (from torch>=1.0->tabgan==1.3.3) (10.3.7.77)\n","Requirement already satisfied: nvidia-cusolver-cu12==11.7.1.2 in /usr/local/lib/python3.12/dist-packages (from torch>=1.0->tabgan==1.3.3) (11.7.1.2)\n","Requirement already satisfied: nvidia-cusparse-cu12==12.5.4.2 in /usr/local/lib/python3.12/dist-packages (from torch>=1.0->tabgan==1.3.3) (12.5.4.2)\n","Requirement already satisfied: nvidia-cusparselt-cu12==0.7.1 in /usr/local/lib/python3.12/dist-packages (from torch>=1.0->tabgan==1.3.3) (0.7.1)\n","Requirement already satisfied: nvidia-nccl-cu12==2.27.3 in /usr/local/lib/python3.12/dist-packages (from torch>=1.0->tabgan==1.3.3) (2.27.3)\n","Requirement already satisfied: nvidia-nvtx-cu12==12.6.77 in /usr/local/lib/python3.12/dist-packages (from torch>=1.0->tabgan==1.3.3) (12.6.77)\n","Requirement already satisfied: nvidia-nvjitlink-cu12==12.6.85 in /usr/local/lib/python3.12/dist-packages (from torch>=1.0->tabgan==1.3.3) (12.6.85)\n","Requirement already satisfied: nvidia-cufile-cu12==1.11.1.6 in /usr/local/lib/python3.12/dist-packages (from torch>=1.0->tabgan==1.3.3) (1.11.1.6)\n","Requirement already satisfied: triton==3.4.0 in /usr/local/lib/python3.12/dist-packages (from torch>=1.0->tabgan==1.3.3) (3.4.0)\n","Requirement already satisfied: patsy>=0.5.1 in /usr/local/lib/python3.12/dist-packages (from category-encoders->tabgan==1.3.3) (1.0.1)\n","Requirement already satisfied: statsmodels>=0.9.0 in /usr/local/lib/python3.12/dist-packages (from category-encoders->tabgan==1.3.3) (0.14.5)\n","Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.12/dist-packages (from pandas->tabgan==1.3.3) (2025.2)\n","Requirement already satisfied: tzdata>=2022.7 in /usr/local/lib/python3.12/dist-packages (from pandas->tabgan==1.3.3) (2025.2)\n","Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.12/dist-packages (from python-dateutil->tabgan==1.3.3) (1.17.0)\n","Requirement already satisfied: pillow!=8.3.*,>=5.3.0 in /usr/local/lib/python3.12/dist-packages (from torchvision->tabgan==1.3.3) (11.3.0)\n","Requirement already satisfied: packaging>=21.3 in /usr/local/lib/python3.12/dist-packages (from statsmodels>=0.9.0->category-encoders->tabgan==1.3.3) (25.0)\n","Requirement already satisfied: mpmath<1.4,>=1.1.0 in /usr/local/lib/python3.12/dist-packages (from sympy>=1.13.3->torch>=1.0->tabgan==1.3.3) (1.3.0)\n","Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.12/dist-packages (from jinja2->torch>=1.0->tabgan==1.3.3) (3.0.3)\n","Downloading tabgan-1.3.3-py2.py3-none-any.whl (28 kB)\n","Downloading category_encoders-2.8.1-py3-none-any.whl (85 kB)\n","\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m85.7/85.7 kB\u001b[0m \u001b[31m2.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hInstalling collected packages: category-encoders, tabgan\n","Successfully installed category-encoders-2.8.1 tabgan-1.3.3\n"]}]}]}