Add files via upload

data4sight · Sep 10, 2022 · 26966a4 · 26966a4
1 parent b569ecb
commit 26966a4
Show file tree

Hide file tree

Showing 36 changed files with 47,282 additions and 0 deletions.
diff --git a/10.1.2.탐색적 데이터 분석(EDA).ipynb b/10.1.2.탐색적 데이터 분석(EDA).ipynb
diff --git a/10.2.3.공분산과 상관성 분석.ipynb b/10.2.3.공분산과 상관성 분석.ipynb
diff --git a/10.3.1.시간 시각화.ipynb b/10.3.1.시간 시각화.ipynb
diff --git a/10.4.1.비교 시각화.ipynb b/10.4.1.비교 시각화.ipynb
diff --git a/10.5.1.분포 시각화.ipynb b/10.5.1.분포 시각화.ipynb
diff --git a/10.6.1.관계 시각화.ipynb b/10.6.1.관계 시각화.ipynb
diff --git a/10.7.1.공간 시각화.ipynb b/10.7.1.공간 시각화.ipynb
diff --git a/10.8.1.박스 플롯.ipynb b/10.8.1.박스 플롯.ipynb
diff --git a/11.1.1.결측값 처리.ipynb b/11.1.1.결측값 처리.ipynb
diff --git a/11.2.1.이상치 처리.ipynb b/11.2.1.이상치 처리.ipynb
diff --git a/11.3.1.변수 구간화(Binning).ipynb b/11.3.1.변수 구간화(Binning).ipynb
diff --git a/11.4.1.데이터 표준화와 정규화 스케일링.ipynb b/11.4.1.데이터 표준화와 정규화 스케일링.ipynb
diff --git a/11.5.1.모델 성능 향상을 위한 파생 변수 생성.ipynb b/11.5.1.모델 성능 향상을 위한 파생 변수 생성.ipynb
diff --git a/11.6.1.슬라이딩 윈도우 데이터 가공.ipynb b/11.6.1.슬라이딩 윈도우 데이터 가공.ipynb
diff --git a/11.7.1.범주형 변수의 가변수 처리.ipynb b/11.7.1.범주형 변수의 가변수 처리.ipynb
diff --git a/11.8.1.클래스 불균형 문제 해결을 위한 언더샘플링과 오버샘플링.ipynb b/11.8.1.클래스 불균형 문제 해결을 위한 언더샘플링과 오버샘플링.ipynb
diff --git a/11.9.2.데이터 거리 측정 방법.ipynb b/11.9.2.데이터 거리 측정 방법.ipynb
diff --git a/12.2.1.주성분 분석(PCA).ipynb b/12.2.1.주성분 분석(PCA).ipynb
diff --git a/12.3.1.공통요인분석 (CFA).ipynb b/12.3.1.공통요인분석 (CFA).ipynb
diff --git a/12.6.1.Z-test와 T-test.ipynb b/12.6.1.Z-test와 T-test.ipynb
diff --git a/12.7.1.ANOVA (Analysis of Variance).ipynb b/12.7.1.ANOVA (Analysis of Variance).ipynb
diff --git a/12.8.1.카이제곱 검정(교차분석).ipynb b/12.8.1.카이제곱 검정(교차분석).ipynb
diff --git a/13.1.4.선형 회귀분석과 Elastic Net.ipynb b/13.1.4.선형 회귀분석과 Elastic Net.ipynb
diff --git a/13.10.3.인공 신경망 (CNN, RNN, LSTM).ipynb b/13.10.3.인공 신경망 (CNN, RNN, LSTM).ipynb
diff --git a/13.2.1.로지스틱 회귀분석.ipynb b/13.2.1.로지스틱 회귀분석.ipynb
diff --git a/13.3.5.의사결정나무와 랜덤 포레스트 (예측,분류모델).ipynb b/13.3.5.의사결정나무와 랜덤 포레스트 (예측,분류모델).ipynb
diff --git a/13.4.3.선형 판별분석과 이차 판별분석 (분류 모델).ipynb b/13.4.3.선형 판별분석과 이차 판별분석 (분류 모델).ipynb
diff --git a/13.5.1.서포트벡터머신 (분류 모델).ipynb b/13.5.1.서포트벡터머신 (분류 모델).ipynb
diff --git a/13.6.1.KNN(K-Nearest Neighbors) (분류, 회귀 모델).ipynb b/13.6.1.KNN(K-Nearest Neighbors) (분류, 회귀 모델).ipynb
diff --git a/13.7.3.시계열 분석 (예측모델).ipynb b/13.7.3.시계열 분석 (예측모델).ipynb
diff --git a/13.8.1.k-means 클러스터링 (군집 모델).ipynb b/13.8.1.k-means 클러스터링 (군집 모델).ipynb
diff --git a/13.9.3.연관규칙과 협업 필터링 (추천 모델).ipynb b/13.9.3.연관규칙과 협업 필터링 (추천 모델).ipynb
diff --git a/14.2.6.주요 교차 검증 방법.ipynb b/14.2.6.주요 교차 검증 방법.ipynb
diff --git a/14.3.7.회귀성능 평가지표.ipynb b/14.3.7.회귀성능 평가지표.ipynb
@@ -0,0 +1,393 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "7a6f6fd1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# 필요한 패키지 설치\n",
+    "\n",
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "from sklearn.linear_model import LinearRegression\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "from sklearn.metrics import mean_squared_error # MSE\n",
+    "from sklearn.metrics import mean_absolute_error # MAE\n",
+    "from sklearn.metrics import mean_absolute_percentage_error # MAPE\n",
+    "from sklearn.metrics import mean_squared_log_error # MSLE"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "d01a91f2",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>id</th>\n",
+       "      <th>date</th>\n",
+       "      <th>price</th>\n",
+       "      <th>bedrooms</th>\n",
+       "      <th>bathrooms</th>\n",
+       "      <th>sqft_living</th>\n",
+       "      <th>sqft_lot</th>\n",
+       "      <th>floors</th>\n",
+       "      <th>waterfront</th>\n",
+       "      <th>view</th>\n",
+       "      <th>...</th>\n",
+       "      <th>grade</th>\n",
+       "      <th>sqft_above</th>\n",
+       "      <th>sqft_basement</th>\n",
+       "      <th>yr_built</th>\n",
+       "      <th>yr_renovated</th>\n",
+       "      <th>zipcode</th>\n",
+       "      <th>lat</th>\n",
+       "      <th>long</th>\n",
+       "      <th>sqft_living15</th>\n",
+       "      <th>sqft_lot15</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>7129300520</td>\n",
+       "      <td>20141013T000000</td>\n",
+       "      <td>221900.0</td>\n",
+       "      <td>3</td>\n",
+       "      <td>1.00</td>\n",
+       "      <td>1180</td>\n",
+       "      <td>5650</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>7</td>\n",
+       "      <td>1180</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1955</td>\n",
+       "      <td>0</td>\n",
+       "      <td>98178</td>\n",
+       "      <td>47.5112</td>\n",
+       "      <td>-122.257</td>\n",
+       "      <td>1340</td>\n",
+       "      <td>5650</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>6414100192</td>\n",
+       "      <td>20141209T000000</td>\n",
+       "      <td>538000.0</td>\n",
+       "      <td>3</td>\n",
+       "      <td>2.25</td>\n",
+       "      <td>2570</td>\n",
+       "      <td>7242</td>\n",
+       "      <td>2.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>7</td>\n",
+       "      <td>2170</td>\n",
+       "      <td>400</td>\n",
+       "      <td>1951</td>\n",
+       "      <td>1991</td>\n",
+       "      <td>98125</td>\n",
+       "      <td>47.7210</td>\n",
+       "      <td>-122.319</td>\n",
+       "      <td>1690</td>\n",
+       "      <td>7639</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>5631500400</td>\n",
+       "      <td>20150225T000000</td>\n",
+       "      <td>180000.0</td>\n",
+       "      <td>2</td>\n",
+       "      <td>1.00</td>\n",
+       "      <td>770</td>\n",
+       "      <td>10000</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>6</td>\n",
+       "      <td>770</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1933</td>\n",
+       "      <td>0</td>\n",
+       "      <td>98028</td>\n",
+       "      <td>47.7379</td>\n",
+       "      <td>-122.233</td>\n",
+       "      <td>2720</td>\n",
+       "      <td>8062</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>2487200875</td>\n",
+       "      <td>20141209T000000</td>\n",
+       "      <td>604000.0</td>\n",
+       "      <td>4</td>\n",
+       "      <td>3.00</td>\n",
+       "      <td>1960</td>\n",
+       "      <td>5000</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>7</td>\n",
+       "      <td>1050</td>\n",
+       "      <td>910</td>\n",
+       "      <td>1965</td>\n",
+       "      <td>0</td>\n",
+       "      <td>98136</td>\n",
+       "      <td>47.5208</td>\n",
+       "      <td>-122.393</td>\n",
+       "      <td>1360</td>\n",
+       "      <td>5000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>1954400510</td>\n",
+       "      <td>20150218T000000</td>\n",
+       "      <td>510000.0</td>\n",
+       "      <td>3</td>\n",
+       "      <td>2.00</td>\n",
+       "      <td>1680</td>\n",
+       "      <td>8080</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>8</td>\n",
+       "      <td>1680</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1987</td>\n",
+       "      <td>0</td>\n",
+       "      <td>98074</td>\n",
+       "      <td>47.6168</td>\n",
+       "      <td>-122.045</td>\n",
+       "      <td>1800</td>\n",
+       "      <td>7503</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>5 rows × 21 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "           id             date     price  bedrooms  bathrooms  sqft_living  \\\n",
+       "0  7129300520  20141013T000000  221900.0         3       1.00         1180   \n",
+       "1  6414100192  20141209T000000  538000.0         3       2.25         2570   \n",
+       "2  5631500400  20150225T000000  180000.0         2       1.00          770   \n",
+       "3  2487200875  20141209T000000  604000.0         4       3.00         1960   \n",
+       "4  1954400510  20150218T000000  510000.0         3       2.00         1680   \n",
+       "\n",
+       "   sqft_lot  floors  waterfront  view  ...  grade  sqft_above  sqft_basement  \\\n",
+       "0      5650     1.0           0     0  ...      7        1180              0   \n",
+       "1      7242     2.0           0     0  ...      7        2170            400   \n",
+       "2     10000     1.0           0     0  ...      6         770              0   \n",
+       "3      5000     1.0           0     0  ...      7        1050            910   \n",
+       "4      8080     1.0           0     0  ...      8        1680              0   \n",
+       "\n",
+       "   yr_built  yr_renovated  zipcode      lat     long  sqft_living15  \\\n",
+       "0      1955             0    98178  47.5112 -122.257           1340   \n",
+       "1      1951          1991    98125  47.7210 -122.319           1690   \n",
+       "2      1933             0    98028  47.7379 -122.233           2720   \n",
+       "3      1965             0    98136  47.5208 -122.393           1360   \n",
+       "4      1987             0    98074  47.6168 -122.045           1800   \n",
+       "\n",
+       "   sqft_lot15  \n",
+       "0        5650  \n",
+       "1        7639  \n",
+       "2        8062  \n",
+       "3        5000  \n",
+       "4        7503  \n",
+       "\n",
+       "[5 rows x 21 columns]"
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# 데이터 불러오기\n",
+    "# https://www.kaggle.com/datasets/harlfoxem/housesalesprediction\n",
+    "df = pd.read_csv(\"datasets/kc_house_data.csv\")\n",
+    "\n",
+    "# 데이터 샘플 확인\n",
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "8e6c73dc",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# 독립변수와 종속변수 분리하여 생성\n",
+    "x = df[[ 'bedrooms', 'bathrooms', 'sqft_living',\n",
+    "       'sqft_lot', 'floors', 'waterfront', 'view', 'condition', 'grade',\n",
+    "       'sqft_above', 'sqft_basement', 'yr_built', 'yr_renovated', \n",
+    "       'sqft_living15', 'sqft_lot15']]\n",
+    "# 'id', 'date'는 키값에 해당하므로 변수에서 제외 해준다.\n",
+    "y = df[['price']]\n",
+    "\n",
+    "# 학습셋과 테스트셋 분리하여 생성(7:3)\n",
+    "# df_train, df_test = train_test_split(df, test_size = 0.4) \n",
+    "x_train, x_test, y_train, y_test = train_test_split(x, y, train_size=0.6, test_size=0.4)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "ffb7e63a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# 다중회귀모델 생성\n",
+    "mreg = LinearRegression(fit_intercept=True)\n",
+    "mreg.fit(x_train, y_train)\n",
+    "\n",
+    "# 테스트셋에 모델 적용\n",
+    "y_predict = mreg.predict(x_test)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "5548daf8",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "RMSE : 214125.86\n",
+      "MAE : 139072.03\n",
+      "MAPE : 0.29\n",
+      "RMSLE : 0.69\n"
+     ]
+    }
+   ],
+   "source": [
+    "# RMSE 산출 (MSE에 루트 적용)\n",
+    "MSE = mean_squared_error(y_test, y_predict)\n",
+    "RMSE = np.sqrt(MSE)\n",
+    "print((\"RMSE : {:.2f}\".format(RMSE)))\n",
+    "\n",
+    "# MAE 산출\n",
+    "MAE = mean_absolute_error(y_test, y_predict)\n",
+    "print((\"MAE : {:.2f}\".format(MAE)))\n",
+    "\n",
+    "# MAPE 산출\n",
+    "MAPE = mean_absolute_percentage_error(y_test, y_predict)\n",
+    "print((\"MAPE : {:.2f}\".format(MAPE)))\n",
+    "\n",
+    "# RMSLE 산출 (MSLE에 루트 적용)\n",
+    "\n",
+    "# 음수값 전처리\n",
+    "y_predict_df = pd.DataFrame(y_predict,columns=['price2'])\n",
+    "y_predict_df2 = y_predict_df.copy()\n",
+    "y_predict_df2.loc[y_predict_df2['price2'] < 0, 'price2'] = 0\n",
+    "y_predict_rmsle = y_predict_df2.to_numpy()\n",
+    "\n",
+    "MSLE = mean_squared_log_error(y_test, (y_predict_rmsle))\n",
+    "RMSLE = np.sqrt(MSLE)\n",
+    "print((\"RMSLE : {:.2f}\".format(RMSLE)))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "3ad066b9",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "C:\\Users\\angry\\AppData\\Local\\Temp\\ipykernel_28972\\1962255028.py:8: RuntimeWarning: invalid value encountered in log\n",
+      "  log_y_predict = np.log(y_predict + 1)\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "price    0.3703\n",
+       "dtype: float64"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# RMSLE ver. 2\n",
+    "  \n",
+    "def rmsle(predicted_values, actual_values):\n",
+    "    \n",
+    "    # 테스트셋 y 값과 예측값에 +1 및 로그 \n",
+    "    log_y_test = np.log(y_test + 1)\n",
+    "    log_y_predict = np.log(y_predict + 1)\n",
+    "\n",
+    "    # 테스트셋 y 값 - 예측값 및 제곱\n",
+    "    diff = log_y_predict - log_y_test\n",
+    "    diff_square = np.square(diff)\n",
+    "\n",
+    "    # 차이값 평균 및 루트\n",
+    "    mean_diff = diff_square.mean()\n",
+    "    final_rmsle = np.sqrt(mean_diff)  \n",
+    "\n",
+    "    return final_rmsle\n",
+    "\n",
+    "rmsle(y_test, y_predict)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.12"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}