{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "   pixel0  pixel1  pixel2  pixel3  pixel4  pixel5  pixel6  pixel7  pixel8  \\\n0       0       0       0       0       0       0       0       0       0   \n1       0       0       0       0       0       0       0       0       0   \n2       0       0       0       0       0       0       0       0       0   \n3       0       0       0       0       0       0       0       0       0   \n4       0       0       0       0       0       0       0       0       0   \n\n   pixel9    ...     pixel774  pixel775  pixel776  pixel777  pixel778  \\\n0       0    ...            0         0         0         0         0   \n1       0    ...            0         0         0         0         0   \n2       0    ...            0         0         0         0         0   \n3       0    ...            0         0         0         0         0   \n4       0    ...            0         0         0         0         0   \n\n   pixel779  pixel780  pixel781  pixel782  pixel783  \n0         0         0         0         0         0  \n1         0         0         0         0         0  \n2         0         0         0         0         0  \n3         0         0         0         0         0  \n4         0         0         0         0         0  \n\n[5 rows x 784 columns]\n0    1\n1    0\n2    1\n3    4\n4    0\nName: label, dtype: int64\n(42000, 784)\n(42000,)\n"
     ]
    }
   ],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "d0 = pd.read_csv('mnist_train.csv')\n",
    "\n",
    "#print(d0)\n",
    "\n",
    "l=d0['label']\n",
    "\n",
    "d=d0.drop('label',axis=1)\n",
    "\n",
    "print(d.head())\n",
    "print(l.head())\n",
    "print(d.shape)\n",
    "print(l.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(42000, 784)\n"
     ]
    }
   ],
   "source": [
    "from sklearn.preprocessing import StandardScaler\n",
    "standardised_data = StandardScaler().fit_transform(d)\n",
    "print(standardised_data.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [],
   "source": [
    "sample_data = standardised_data\n",
    "from sklearn import decomposition\n",
    "pca = decomposition.PCA()\n",
    "pca.n_components = 2\n",
    "pca_data = pca.fit_transform(sample_data)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(42000, 2)\n"
     ]
    }
   ],
   "source": [
    "print(pca_data.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [],
   "source": [
    "pca_data = np.vstack((pca_data.T,l)).T\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(42000, 3)\n"
     ]
    }
   ],
   "source": [
    "print(pca_data.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [],
   "source": [
    "import seaborn as sn\n",
    "\n",
    "pca_dataframe = pd.DataFrame(pca_data,columns = (\"1st_principal\",\"2nd_principal\",\"Lables\"))\n",
    "\n",
    "sn.FacetGrid(pca_dataframe , hue = \"Lables\", height=6).map(plt.scatter ,\"1st_principal\",\"2nd_principal\").add_legend()\n",
    "\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "t-SNE done! Time elapsed: 4151.372444868088 seconds\n"
     ]
    }
   ],
   "source": [
    "from sklearn.manifold import TSNE\n",
    "import time\n",
    "\n",
    "time_start = time.time()\n",
    "model = TSNE(n_components = 2, random_state = 0)\n",
    "# configuring the parameteres\n",
    "# the number of components = 2\n",
    "# default perplexity = 30\n",
    "# default learning rate = 200\n",
    "# default Maximum number of iterations for the optimization = 1000\n",
    "\n",
    "tsne_data = model.fit_transform(standardised_data)\n",
    "print('t-SNE done! Time elapsed: {} seconds'.format(time.time()-time_start))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(42000, 2)\n(42000, 3)\n"
     ]
    }
   ],
   "source": [
    "print(tsne_data.shape)\n",
    "tsne_data = np.vstack((tsne_data.T,l)).T\n",
    "print(tsne_data.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {},
   "outputs": [],
   "source": [
    "tsne_dataframe = pd.DataFrame(data=tsne_data, columns=(\"Dim_1\", \"Dim_2\", \"label\"))\n",
    "\n",
    "sn.FacetGrid(data=tsne_dataframe, hue=\"label\", height=15).map(plt.scatter,\"Dim_1\", \"Dim_2\").add_legend()\n",
    "\n",
    "plt.show()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 2",
   "language": "python",
   "name": "python2"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 2
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython2",
   "version": "2.7.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}