{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.feature_selection import VarianceThreshold\n",
    "import pandas as pd\n",
    "from scipy.stats import pearsonr, spearmanr\n",
    "from sklearn.decomposition import PCA"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 低方差特征过滤"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "# 读取数据\n",
    "data = pd.read_csv('./data/factor_returns.csv')\n",
    "\n",
    "x = data.iloc[:, 1:10]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(2318, 9)"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "x.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "# 初始化转换器\n",
    "transfer = VarianceThreshold(threshold=1.0)\n",
    "res = transfer.fit_transform(x)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(2318, 8)"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "res.shape"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 相关系数"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "x1 = [12.5, 15.3, 23.2, 26.4, 33.5, 34.4, 39.4, 45.2, 55.4, 60.9]\n",
    "x2 = [21.2, 23.9, 32.9, 34.1, 42.5, 43.2, 49.0, 52.8, 59.4, 63.5]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(0.9941983762371883, 4.9220899554573455e-09)"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# 皮尔逊相关系数\n",
    "pearsonr(x1, x2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "SpearmanrResult(correlation=0.9999999999999999, pvalue=6.646897422032013e-64)"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# 斯皮尔曼相关系数\n",
    "spearmanr(x1,x2)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## PCA"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [],
   "source": [
    "data = [[2,8,4,5],\n",
    "[6,3,0,8],\n",
    "[5,4,9,1]]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[ 1.22879107e-15,  3.82970843e+00],\n",
       "       [ 5.74456265e+00, -1.91485422e+00],\n",
       "       [-5.74456265e+00, -1.91485422e+00]])"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# 初始化转换器\n",
    "transfer = PCA(n_components=0.9)\n",
    "# 转换数据\n",
    "transfer.fit_transform(data)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[ 1.22879107e-15,  3.82970843e+00,  2.65047672e-17],\n",
       "       [ 5.74456265e+00, -1.91485422e+00,  2.65047672e-17],\n",
       "       [-5.74456265e+00, -1.91485422e+00,  2.65047672e-17]])"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# 初始化转换器\n",
    "transfer = PCA(n_components=3)\n",
    "# 转换数据\n",
    "transfer.fit_transform(data)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "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": "3.7.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}