From f8bc1216ef76ea1a8d26910ce1c06f2e92f75afd Mon Sep 17 00:00:00 2001
From: "hy.kim" <hy.kim@gesolutions.co.kr>
Date: Wed, 20 Sep 2023 17:26:23 +0900
Subject: [PATCH] init

---
 regression.ipynb | 179 +++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 179 insertions(+)
 create mode 100644 regression.ipynb

diff --git a/regression.ipynb b/regression.ipynb
new file mode 100644
index 0000000..301b074
--- /dev/null
+++ b/regression.ipynb
@@ -0,0 +1,179 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# 선형 회귀 (Linear Regression)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Coefficients: [[2.50779446]]\n",
+      "Intercept: [4.64634325]\n"
+     ]
+    }
+   ],
+   "source": [
+    "from sklearn.linear_model import LinearRegression\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "import numpy as np\n",
+    "\n",
+    "# 예제 데이터 생성\n",
+    "X = np.random.rand(100, 1) * 10  # 100개의 랜덤 데이터\n",
+    "y = 2.5 * X + 5 + np.random.randn(100, 1) * 2  # y = 2.5x + 5 + 잡음\n",
+    "\n",
+    "# 데이터 분할\n",
+    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)\n",
+    "\n",
+    "# 선형 회귀 모델 학습\n",
+    "model = LinearRegression()\n",
+    "model.fit(X_train, y_train)\n",
+    "\n",
+    "# 예측\n",
+    "y_pred = model.predict(X_test)\n",
+    "\n",
+    "print(\"Coefficients:\", model.coef_)\n",
+    "print(\"Intercept:\", model.intercept_)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Mean Squared Error: 4061.83\n"
+     ]
+    }
+   ],
+   "source": [
+    "import numpy as np\n",
+    "from sklearn import datasets\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "from sklearn.linear_model import LinearRegression\n",
+    "from sklearn.metrics import mean_squared_error\n",
+    "\n",
+    "# 데이터 로드\n",
+    "diabetes = datasets.load_diabetes()\n",
+    "X = diabetes.data[:, np.newaxis, 2]  # BMI feature만 사용\n",
+    "y = diabetes.target\n",
+    "\n",
+    "# 데이터 분할\n",
+    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)\n",
+    "\n",
+    "# 선형 회귀 모델 학습\n",
+    "model = LinearRegression()\n",
+    "model.fit(X_train, y_train)\n",
+    "\n",
+    "# 예측 및 평가\n",
+    "y_pred = model.predict(X_test)\n",
+    "mse = mean_squared_error(y_test, y_pred)\n",
+    "print(f\"Mean Squared Error: {mse:.2f}\")\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# 로지스틱 회귀 (Logistic Regression)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sklearn.linear_model import LogisticRegression\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "\n",
+    "# 예제 데이터 생성\n",
+    "X = np.random.rand(100, 1) * 10  # 100개의 랜덤 데이터\n",
+    "y = (X > 5).astype(int).ravel()  # X가 5보다 크면 1, 아니면 0\n",
+    "\n",
+    "# 데이터 분할\n",
+    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)\n",
+    "\n",
+    "# 로지스틱 회귀 모델 학습\n",
+    "model = LogisticRegression()\n",
+    "model.fit(X_train, y_train)\n",
+    "\n",
+    "# 예측\n",
+    "y_pred = model.predict(X_test)\n",
+    "\n",
+    "print(\"Coefficients:\", model.coef_)\n",
+    "print(\"Intercept:\", model.intercept_)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Accuracy: 95.61%\n"
+     ]
+    }
+   ],
+   "source": [
+    "from sklearn import datasets\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "from sklearn.linear_model import LogisticRegression\n",
+    "from sklearn.metrics import accuracy_score\n",
+    "\n",
+    "# 데이터 로드\n",
+    "cancer = datasets.load_breast_cancer()\n",
+    "X = cancer.data\n",
+    "y = cancer.target\n",
+    "\n",
+    "# 데이터 분할\n",
+    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)\n",
+    "\n",
+    "# 로지스틱 회귀 모델 학습\n",
+    "model = LogisticRegression(max_iter=10000)  # max_iter를 증가시켜 수렴을 도움\n",
+    "model.fit(X_train, y_train)\n",
+    "\n",
+    "# 예측 및 평가\n",
+    "y_pred = model.predict(X_test)\n",
+    "acc = accuracy_score(y_test, y_pred)\n",
+    "print(f\"Accuracy: {acc*100:.2f}%\")\n"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "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": "3.10.11"
+  },
+  "orig_nbformat": 4
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}