diff --git "a/Analysis_code/find_reason/seoul.ipynb" "b/Analysis_code/find_reason/seoul.ipynb"
deleted file mode 100644--- "a/Analysis_code/find_reason/seoul.ipynb"
+++ /dev/null
@@ -1,1023 +0,0 @@
-{
- "cells": [
- {
- "cell_type": "code",
- "execution_count": 1,
- "metadata": {},
- "outputs": [
- {
- "name": "stderr",
- "output_type": "stream",
- "text": [
- "2025-06-05 04:48:52.680997: I tensorflow/core/util/port.cc:110] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.\n",
- "2025-06-05 04:48:52.705732: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.\n",
- "To enable the following instructions: AVX2 AVX_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.\n",
- "2025-06-05 04:48:53.125365: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT\n"
- ]
- }
- ],
- "source": [
- "# 분석에 필요한 라이브러리 임포트\n",
- "import warnings\n",
- "warnings.filterwarnings('ignore')\n",
- "import pandas as pd\n",
- "import numpy as np\n",
- "import matplotlib.pyplot as plt\n",
- "import seaborn as sns\n",
- "from scipy import stats\n",
- "from scipy.spatial import distance\n",
- "from scipy.stats import wasserstein_distance, entropy, ks_2samp\n",
- "from sklearn.manifold import TSNE\n",
- "from sklearn.preprocessing import StandardScaler\n",
- "from sklearn.ensemble import RandomForestRegressor\n",
- "from sklearn.ensemble import RandomForestClassifier # Added\n",
- "from sklearn.model_selection import train_test_split # Added\n",
- "from sklearn.metrics import roc_auc_score # Added\n",
- "from statsmodels.distributions.empirical_distribution import ECDF # Added\n",
- "import umap\n",
- "\n",
- "# 한글 폰트 설정\n",
- "plt.rcParams['font.family'] = 'NanumGothic'\n",
- "plt.rcParams['axes.unicode_minus'] = False"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 2,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Index(['datetime', 'temp_C', 'precip_mm', 'wind_speed', 'wind_dir', 'hm',\n",
- " 'vap_pressure', 'dewpoint_C', 'loc_pressure', 'sea_pressure',\n",
- " 'solarRad', 'snow_cm', 'cloudcover', 'lm_cloudcover', 'low_cloudbase',\n",
- " 'groundtemp', 'O3', 'NO2', 'PM10', 'PM25', 'multi_class',\n",
- " 'binary_class', 'year', 'month', 'hour', 'ground_temp - temp_C',\n",
- " 'hour_sin', 'hour_cos', 'month_sin', 'month_cos', 'visi'],\n",
- " dtype='object')\n"
- ]
- }
- ],
- "source": [
- "seoul = pd.read_feather(\"../../data/data_for_modeling/df_seoul.feather\")\n",
- "print(seoul.columns)\n",
- "seoul= seoul[['datetime','hm','PM10','PM25','year','month','hour','multi_class']]"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 3,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "datetime 0\n",
- "hm 0\n",
- "PM10 0\n",
- "PM25 0\n",
- "year 0\n",
- "month 0\n",
- "hour 0\n",
- "multi_class 0\n",
- "dtype: int64"
- ]
- },
- "execution_count": 3,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "pd.isna(seoul).sum()"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 4,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "(52584, 8)"
- ]
- },
- "execution_count": 4,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "seoul.shape"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 5,
- "metadata": {},
- "outputs": [],
- "source": [
- "from sklearn.decomposition import PCA\n",
- "\n",
- "# 특성 선택 (예: PM10, PM25, hm 등)\n",
- "features = seoul[['PM10', 'PM25', 'hm']]\n",
- "# 스케일링\n",
- "scaler = StandardScaler()\n",
- "scaled_features = scaler.fit_transform(features)\n",
- "# PCA 수행\n",
- "pca = PCA(n_components=2)\n",
- "pca_result = pca.fit_transform(scaled_features)\n"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 6,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "(52584, 2)"
- ]
- },
- "execution_count": 6,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "pca_result.shape"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 7,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/html": [
- "\n",
- "\n",
- "
\n",
- " \n",
- " \n",
- " | \n",
- " datetime | \n",
- " year | \n",
- " month | \n",
- " hour | \n",
- " multi_class | \n",
- " pca_x | \n",
- " pca_y | \n",
- "
\n",
- " \n",
- " \n",
- " \n",
- " | 0 | \n",
- " 2018-01-01 00:00:00 | \n",
- " 2018 | \n",
- " 1 | \n",
- " 0 | \n",
- " 2 | \n",
- " -0.198032 | \n",
- " -1.165834 | \n",
- "
\n",
- " \n",
- " | 1 | \n",
- " 2018-01-01 01:00:00 | \n",
- " 2018 | \n",
- " 1 | \n",
- " 1 | \n",
- " 2 | \n",
- " -0.007260 | \n",
- " -1.085779 | \n",
- "
\n",
- " \n",
- " | 2 | \n",
- " 2018-01-01 02:00:00 | \n",
- " 2018 | \n",
- " 1 | \n",
- " 2 | \n",
- " 2 | \n",
- " -0.387762 | \n",
- " -1.088096 | \n",
- "
\n",
- " \n",
- " | 3 | \n",
- " 2018-01-01 03:00:00 | \n",
- " 2018 | \n",
- " 1 | \n",
- " 3 | \n",
- " 2 | \n",
- " -0.423208 | \n",
- " -0.989392 | \n",
- "
\n",
- " \n",
- " | 4 | \n",
- " 2018-01-01 04:00:00 | \n",
- " 2018 | \n",
- " 1 | \n",
- " 4 | \n",
- " 2 | \n",
- " -0.436776 | \n",
- " -0.532494 | \n",
- "
\n",
- " \n",
- "
\n",
- "