{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# SVM不同核函数及其参数对分类性能"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "王**"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 导入"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Populating the interactive namespace from numpy and matplotlib\n"
     ]
    }
   ],
   "source": [
    "%pylab inline\n",
    "\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "from sklearn.linear_model import SGDClassifier\n",
    "from sklearn.datasets.samples_generator import make_blobs\n",
    "from sklearn.preprocessing import StandardScaler\n",
    "from matplotlib.colors import ListedColormap\n",
    "from skimage import io,data\n",
    "\n",
    "from sklearn.feature_selection import RFE\n",
    "from sklearn.ensemble import GradientBoostingClassifier, IsolationForest\n",
    "from sklearn.externals import joblib\n",
    "from sklearn.model_selection  import train_test_split\n",
    "import numpy.ma as ma\n",
    "import os, shutil"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": true
   },
   "source": [
    "## 读取数据"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(392960,)\n",
      "(392960, 191)\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "array([  2,   3,  51, 102, 153, 204, 255], dtype=int16)"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from skimage.io import imread\n",
    "img = imread('E:\\Hyperspectral_Project\\dc.tif')\n",
    "roi = io.imread('E:\\Hyperspectral_Project\\protest.tif')\n",
    "\n",
    "img = np.transpose(img,(1,2,0))#(1280, 307,191)\n",
    "labels = np.unique(roi[roi > 0])\n",
    "X =img.reshape(392960,191)\n",
    "t =img.reshape(392960,191)\n",
    "\n",
    "Y=roi[:,:,0]\n",
    "np.unique(Y)\n",
    "\n",
    "Y=Y.ravel()\n",
    "\n",
    "print(Y.shape)\n",
    "print(X.shape)\n",
    "\n",
    "X = X[Y>0,:]\n",
    "Y = Y[Y>0]\n",
    "\n",
    "np.unique(Y)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.linear_model import LogisticRegression\n",
    "from sklearn.metrics import accuracy_score\n",
    "from ipywidgets import interact,interact_manual"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "X_train, X_test, y_train, y_test = train_test_split(\n",
    "        X,\n",
    "        Y,\n",
    "        train_size=0.75,\n",
    "        random_state= 42,\n",
    "        stratify=Y)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "X_train, X_valid, y_train, y_valid = train_test_split(\n",
    "        X_train,\n",
    "        y_train,\n",
    "        train_size=0.66,\n",
    "        random_state= 0,\n",
    "        stratify=y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "collapsed": true,
    "scrolled": true
   },
   "outputs": [],
   "source": [
    "#训练模型\n",
    "from sklearn.svm import SVC\n",
    "\n",
    "clf = SVC(kernel='linear').fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1.0"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "clf.score(X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.99921104536489147"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "clf.score(X_valid, y_valid)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.99758551307847088"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y_model = clf.predict(X_test)\n",
    "accuracy_score(y_test, y_model)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import seaborn as sns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAVcAAAFXCAYAAAAWMQ0YAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nVxERA1SuIiIG/B8c6Oa5jYvJPwAAAABJRU5ErkJggg==\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0xc5fcdd8>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "from sklearn.metrics import confusion_matrix\n",
    "\n",
    "mat = confusion_matrix(y_test, y_model)\n",
    "\n",
    "sns.heatmap(mat, square=True, annot=True,fmt='d', cbar=False)\n",
    "plt.xlabel('predicted value')\n",
    "plt.ylabel('true value');"
   ]
  }
 ],
 "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": "3.6.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}