diff --git "a/Analysis_code/find_reason/daejeon.ipynb" "b/Analysis_code/find_reason/daejeon.ipynb"
deleted file mode 100644--- "a/Analysis_code/find_reason/daejeon.ipynb"
+++ /dev/null
@@ -1,1012 +0,0 @@
-{
- "cells": [
- {
- "cell_type": "code",
- "execution_count": 32,
- "metadata": {},
- "outputs": [],
- "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": 33,
- "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": [
- "daejeon = pd.read_feather(\"../../data/data_for_modeling/df_daejeon.feather\")\n",
- "print(daejeon.columns)\n",
- "daejeon= daejeon[['datetime','hm','PM10','PM25','year','month','hour','multi_class']]"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 34,
- "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": 34,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "pd.isna(daejeon).sum()"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 35,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "(52584, 8)"
- ]
- },
- "execution_count": 35,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "daejeon.shape"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 36,
- "metadata": {},
- "outputs": [],
- "source": [
- "from sklearn.decomposition import PCA\n",
- "\n",
- "# 특성 선택 (예: PM10, PM25, hm 등)\n",
- "features = daejeon[['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": 37,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "(52584, 2)"
- ]
- },
- "execution_count": 37,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "pca_result.shape"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 38,
- "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",
- " 0.005792 | \n",
- " 0.073476 | \n",
- "
\n",
- " \n",
- " | 1 | \n",
- " 2018-01-01 01:00:00 | \n",
- " 2018 | \n",
- " 1 | \n",
- " 1 | \n",
- " 2 | \n",
- " -0.275947 | \n",
- " -0.230940 | \n",
- "
\n",
- " \n",
- " | 2 | \n",
- " 2018-01-01 02:00:00 | \n",
- " 2018 | \n",
- " 1 | \n",
- " 2 | \n",
- " 2 | \n",
- " 0.053721 | \n",
- " -0.300757 | \n",
- "
\n",
- " \n",
- " | 3 | \n",
- " 2018-01-01 03:00:00 | \n",
- " 2018 | \n",
- " 1 | \n",
- " 3 | \n",
- " 2 | \n",
- " 0.339214 | \n",
- " -0.106698 | \n",
- "
\n",
- " \n",
- " | 4 | \n",
- " 2018-01-01 04:00:00 | \n",
- " 2018 | \n",
- " 1 | \n",
- " 4 | \n",
- " 2 | \n",
- " -0.149142 | \n",
- " 0.164801 | \n",
- "
\n",
- " \n",
- "
\n",
- "