Skip to content

Instantly share code, notes, and snippets.

@rakuishi

rakuishi/20180225_multiple-linear-regression_1.ipynb

Last active February 3, 2022 02:14
Show Gist options
  • Save rakuishi/5e56cb5044495fb79f7630b0d4f7bf4d to your computer and use it in GitHub Desktop.
Save rakuishi/5e56cb5044495fb79f7630b0d4f7bf4d to your computer and use it in GitHub Desktop.
Download ZIP
【キカガク流】人工知能・機械学習 脱ブラックボックス講座 - 中級編 -
Display the source blob
Display the rendered blob
Raw
20180225_multiple-linear-regression_1.ipynb
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# 行列演算の基礎"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"$\\boldsymbol{w} = (\\boldsymbol{X}^{T}\\boldsymbol{X})^{-1}\\boldsymbol{X}^{T}\\boldsymbol{y}$"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"- ベクトルの定義\n",
"- 行列の定義\n",
"- 転置\n",
"- 逆行列\n",
"- 行列積"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"import numpy as np"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[[1]\n",
" [2]\n",
" [3]]\n"
]
}
],
"source": [
"# ベクトルの定義\n",
"x = np.array([[1], [2], [3]])\n",
"print(x)"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[[1 2]\n",
" [3 4]]\n"
]
}
],
"source": [
"# 行列の定義\n",
"X = np.array([[1, 2], [3, 4]])\n",
"print(X)"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[[1 3]\n",
" [2 4]]\n"
]
}
],
"source": [
"# 転置\n",
"Xt = X.T\n",
"print(Xt)"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[[-2. 1. ]\n",
" [ 1.5 -0.5]]\n"
]
}
],
"source": [
"# 逆行列\n",
"# linear algebra: 線形代数\n",
"X_inv = np.linalg.inv(X)\n",
"print(X_inv)"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[[ 1.00000000e+00 1.11022302e-16]\n",
" [ 0.00000000e+00 1.00000000e+00]]\n"
]
}
],
"source": [
"# 行列積\n",
"XX_inv = np.dot(X, X_inv)\n",
"print(XX_inv)"
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"array([[1],\n",
" [2],\n",
" [3]])"
]
},
"execution_count": 17,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"x"
]
},
{
"cell_type": "code",
"execution_count": 18,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"array([[1, 2, 3]])"
]
},
"execution_count": 18,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"x.T"
]
},
{
"cell_type": "code",
"execution_count": 19,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[[2 3 4]\n",
" [1 2 3]]\n"
]
}
],
"source": [
"X = np.array([\n",
" [2, 3, 4],\n",
" [1, 2, 3],\n",
"])\n",
"print(X)"
]
},
{
"cell_type": "code",
"execution_count": 20,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"(2, 3)"
]
},
"execution_count": 20,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"X.shape"
]
},
{
"cell_type": "code",
"execution_count": 22,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"row, col = X.shape"
]
},
{
"cell_type": "code",
"execution_count": 23,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"2 3\n"
]
}
],
"source": [
"print(row, col)"
]
},
{
"cell_type": "code",
"execution_count": 24,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[2 3 4]\n",
"[1 2 3]\n"
]
}
],
"source": [
"for x in X:\n",
" print(x)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# 演習問題"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"$\\boldsymbol{w} = (\\boldsymbol{X}^{T}\\boldsymbol{X})^{-1}\\boldsymbol{X}^{T}\\boldsymbol{y}$"
]
},
{
"cell_type": "code",
"execution_count": 26,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[[1 2 3]\n",
" [1 2 5]\n",
" [1 3 4]\n",
" [1 5 9]]\n",
"[[1]\n",
" [5]\n",
" [6]\n",
" [8]]\n"
]
}
],
"source": [
"X = np.array([\n",
" [1, 2, 3],\n",
" [1, 2, 5],\n",
" [1, 3, 4],\n",
" [1, 5, 9],\n",
"])\n",
"print(X)\n",
"\n",
"y = np.array([\n",
" [1],\n",
" [5],\n",
" [6],\n",
" [8],\n",
"])\n",
"print(y)"
]
},
{
"cell_type": "code",
"execution_count": 30,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[[ 4 12 21]\n",
" [ 12 42 73]\n",
" [ 21 73 131]]\n"
]
}
],
"source": [
"Xt = X.T\n",
"XtX = np.dot(Xt, X)\n",
"print(XtX)"
]
},
{
"cell_type": "code",
"execution_count": 31,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[[ 1.76530612 -0.39795918 -0.06122449]\n",
" [-0.39795918 0.84693878 -0.40816327]\n",
" [-0.06122449 -0.40816327 0.24489796]]\n"
]
}
],
"source": [
"XtX_inv = np.linalg.inv(XtX)\n",
"print(XtX_inv)"
]
},
{
"cell_type": "code",
"execution_count": 32,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[[ 20]\n",
" [ 70]\n",
" [124]]\n"
]
}
],
"source": [
"Xty = np.dot(Xt, y)\n",
"print(Xty)"
]
},
{
"cell_type": "code",
"execution_count": 33,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[[-0.14285714]\n",
" [ 0.71428571]\n",
" [ 0.57142857]]\n"
]
}
],
"source": [
"w = np.dot(XtX_inv, Xty)\n",
"print(w)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Scikit-learn"
]
},
{
"cell_type": "code",
"execution_count": 35,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"from sklearn.linear_model import LinearRegression"
]
},
{
"cell_type": "code",
"execution_count": 36,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"LinearRegression(copy_X=True, fit_intercept=True, n_jobs=1, normalize=False)"
]
},
"execution_count": 36,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# モデルの宣言\n",
"model = LinearRegression()\n",
"\n",
"# モデルの学習 ← パラメータの調整\n",
"model.fit(X, y)"
]
},
{
"cell_type": "code",
"execution_count": 37,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"array([[ 0. , 0.71428571, 0.57142857]])"
]
},
"execution_count": 37,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# 調整後のパラメータ\n",
"model.coef_"
]
},
{
"cell_type": "code",
"execution_count": 38,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"array([-0.14285714])"
]
},
"execution_count": 38,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"model.intercept_"
]
},
{
"cell_type": "code",
"execution_count": 39,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"0.69230769230769229"
]
},
"execution_count": 39,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# 予測精度 ← 決定係数\n",
"model.score(X, y)"
]
},
{
"cell_type": "code",
"execution_count": 42,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[[ 3.]]\n"
]
}
],
"source": [
"# 予測値の計算\n",
"x = np.array([[1, 2, 3]])\n",
"y_pred = model.predict(x)\n",
"print(y_pred)"
]
}
],
"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": "3.6.3"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
Display the source blob
Display the rendered blob
Raw
20180225_multiple-linear-regression_2.ipynb
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Display the source blob
Display the rendered blob
Raw
20180301_multiple-linear-regression_3.ipynb
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
@rakuishi
Copy link
Author

rakuishi commented Mar 3, 2018

pairplot

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment