added setup.py

Author: lambdaofgod

notebooks/COIL20 Manifold Learning.ipynb

@@ -2,9 +2,9 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 23,
+   "execution_count": 1,
    "metadata": {
-    "collapsed": true
+    "scrolled": true
    },
    "outputs": [],
    "source": [
@@ -19,9 +19,7 @@
     "\n",
     "from sklearn.datasets import fetch_20newsgroups\n",
     "\n",
-    "\n",
-    "%run ../src/load_data_utils.py\n",
-    "%run ../src/glove_2_word2vec.py"
+    "from src import load_data_utils, glove_2_word2vec"
    ]
   },
   {

notebooks/Word Embeddings on 20 Newsgroups.ipynb

@@ -11,23 +11,17 @@
    "cell_type": "code",
    "execution_count": 1,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "/home/kuba/Projects/notebooks/examples-counterexamples/src\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
-    "cd ../../src"
+    "from src import fetch_mnist, neural_nets"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 2,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "import matplotlib.pyplot as plt\n",
@@ -97,7 +91,9 @@
   {
    "cell_type": "code",
    "execution_count": 5,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "shared_args = (dict(\n",

notebooks/neural_nets/Autoencoders.ipynb

@@ -22,28 +22,32 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "/home/kuba/Projects/notebooks/examples-counterexamples/src\n"
-     ]
-    }
-   ],
+   "execution_count": null,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
    "source": [
-    "cd ../../src"
+    "from src import *"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 2,
-   "metadata": {
-    "collapsed": true
-   },
-   "outputs": [],
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "ImportError",
+     "evalue": "No module named 'fetch_mnist'",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mImportError\u001b[0m                               Traceback (most recent call last)",
+      "\u001b[0;32m<ipython-input-2-624215dda5bd>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m      7\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mtheano\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtensor\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0mT\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      8\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 9\u001b[0;31m \u001b[0;32mfrom\u001b[0m \u001b[0mfetch_mnist\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mpreprocessed_mnist\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     10\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0mneural_nets\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mlogistic_regression\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mLogisticRegression\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     11\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0mneural_nets\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mplotting_utils\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mPlotter\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;31mImportError\u001b[0m: No module named 'fetch_mnist'"
+     ]
+    }
+   ],
    "source": [
     "import matplotlib.pyplot as plt\n",
     "%matplotlib inline\n",

notebooks/neural_nets/Logistic Regression.ipynb

@@ -3,24 +3,9 @@
   {
    "cell_type": "code",
    "execution_count": 1,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "/home/kuba/Projects/notebooks/examples-counterexamples/src\n"
-     ]
-    }
-   ],
-   "source": [
-    "cd ../../src"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "from __future__ import print_function\n",
@@ -34,12 +19,12 @@
     "%matplotlib inline\n",
     "import matplotlib.pyplot as plt\n",
     "\n",
-    "from fetch_mnist import preprocessed_mnist"
+    "from src.fetch_mnist import preprocessed_mnist"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [
     {
@@ -78,8 +63,10 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
-   "metadata": {},
+   "execution_count": 3,
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "data = sym.Variable('data')\n",
@@ -91,7 +78,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 4,
    "metadata": {
     "collapsed": true
    },
@@ -112,13 +99,13 @@
     "                message = 'Iter[{}] Batch[{}] Train-{}={}'.format(*message_args)\n",
     "                if print_log:\n",
     "                  print(message)\n",
-    "                lsb.append(message, message_args)\n",
+    "                lst.append((message, message_args))\n",
     "    return _callback"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 5,
    "metadata": {
     "scrolled": false
    },
@@ -127,8 +114,8 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "CPU times: user 24.4 s, sys: 844 ms, total: 25.3 s\n",
-      "Wall time: 12.2 s\n"
+      "CPU times: user 25.5 s, sys: 1.29 s, total: 26.8 s\n",
+      "Wall time: 13 s\n"
      ]
     }
    ],
@@ -143,8 +130,10 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
-   "metadata": {},
+   "execution_count": 6,
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "y_test_pred_proba = nn.predict(test_iter)\n",
@@ -153,16 +142,16 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "0.89400000000000002"
+       "0.89242857142857146"
       ]
      },
-     "execution_count": 9,
+     "execution_count": 7,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -175,8 +164,10 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
-   "metadata": {},
+   "execution_count": 8,
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "accs = [msg[1][3] for msg in log_list]"
@@ -191,24 +182,24 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": 9,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "[<matplotlib.lines.Line2D at 0x7f0790ef81d0>]"
+       "[<matplotlib.lines.Line2D at 0x7fca28066c88>]"
       ]
      },
-     "execution_count": 19,
+     "execution_count": 9,
      "metadata": {},
      "output_type": "execute_result"
     },
     {
      "data": {
       "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXcAAAD8CAYAAACMwORRAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nEZEq9P8B1mxZLmU1oJ4AAAAASUVORK5CYII=\n",
       "text/plain": [
-       "<matplotlib.figure.Figure at 0x7f0790f4b198>"
+       "<matplotlib.figure.Figure at 0x7fca284d6a20>"
       ]
      },
      "metadata": {},

notebooks/neural_nets/MXNet basics.ipynb

@@ -22,23 +22,17 @@
    "cell_type": "code",
    "execution_count": 1,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "/home/kuba/Projects/notebooks/examples-counterexamples/src\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
-    "cd ../../src"
+    "from src import fetch_mnist, neural_nets"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 2,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "import matplotlib.pyplot as plt\n",

notebooks/neural_nets/Multilayer Perceptron.ipynb

@@ -0,0 +1,6 @@
+from setuptools import setup
+
+
+setup(
+    name='examples_counterexamples'
+)