{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "# Deep Neural Network - A Hands-on Challenge course\n", "## Jupyter Notebook Walkthrough\n", "### Weizmann Institute of science, Spring 2017" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "
" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# Loading and \"Tasting\" Data" ] }, { "cell_type": "code", "execution_count": 16, "metadata": { "collapsed": true }, "outputs": [], "source": [ "import pandas as pd" ] }, { "cell_type": "code", "execution_count": 19, "metadata": { "collapsed": false }, "outputs": [ { "data": { "text/html": [ "
\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
TimestampExerciseTypeIntensityDuration
ConnectionIDEventID
269392013-02-18 06:01:00Anaerobic2.045
9402013-02-18 06:47:00Aerobic2.040
9412013-02-19 07:02:00Aerobic3.077
9422013-02-20 06:33:00Anaerobic2.040
9432013-02-20 08:01:00Aerobic2.040
\n", "
" ], "text/plain": [ " Timestamp ExerciseType Intensity Duration\n", "ConnectionID EventID \n", "26 939 2013-02-18 06:01:00 Anaerobic 2.0 45\n", " 940 2013-02-18 06:47:00 Aerobic 2.0 40\n", " 941 2013-02-19 07:02:00 Aerobic 3.0 77\n", " 942 2013-02-20 06:33:00 Anaerobic 2.0 40\n", " 943 2013-02-20 08:01:00 Aerobic 2.0 40" ] }, "execution_count": 19, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df = pd.read_pickle('Exercises.df')\n", "df.head()" ] }, { "cell_type": "code", "execution_count": 22, "metadata": { "collapsed": false }, "outputs": [ { "data": { "text/html": [ "
\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
TimestampExerciseTypeIntensityDuration
ConnectionIDEventID
13781356012016-04-12 08:00:25Yoga & Pilates4.052
1356622016-04-13 07:50:25Cycling2.010
1356632016-04-13 08:05:43Yoga & Pilates2.055
13821399822016-09-26 14:00:00Other2.010
13831401712016-09-30 18:15:51Walking2.040
\n", "
" ], "text/plain": [ " Timestamp ExerciseType Intensity Duration\n", "ConnectionID EventID \n", "1378 135601 2016-04-12 08:00:25 Yoga & Pilates 4.0 52\n", " 135662 2016-04-13 07:50:25 Cycling 2.0 10\n", " 135663 2016-04-13 08:05:43 Yoga & Pilates 2.0 55\n", "1382 139982 2016-09-26 14:00:00 Other 2.0 10\n", "1383 140171 2016-09-30 18:15:51 Walking 2.0 40" ] }, "execution_count": 22, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df.tail()" ] }, { "cell_type": "code", "execution_count": 24, "metadata": { "collapsed": false }, "outputs": [ { "data": { "text/plain": [ "(3522, 4)" ] }, "execution_count": 24, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df.shape" ] }, { "cell_type": "code", "execution_count": 26, "metadata": { "collapsed": false }, "outputs": [ { "data": { "text/plain": [ "Index(['Timestamp', 'ExerciseType', 'Intensity', 'Duration'], dtype='object')" ] }, "execution_count": 26, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df.columns" ] }, { "cell_type": "code", "execution_count": 28, "metadata": { "collapsed": false }, "outputs": [ { "data": { "text/html": [ "
\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
IntensityDuration
count3522.0000003522.000000
mean2.80494042.880182
std1.08447436.507279
min1.000000-84.000000
25%2.00000020.000000
50%3.00000035.000000
75%3.00000060.000000
max5.000000420.000000
\n", "
" ], "text/plain": [ " Intensity Duration\n", "count 3522.000000 3522.000000\n", "mean 2.804940 42.880182\n", "std 1.084474 36.507279\n", "min 1.000000 -84.000000\n", "25% 2.000000 20.000000\n", "50% 3.000000 35.000000\n", "75% 3.000000 60.000000\n", "max 5.000000 420.000000" ] }, "execution_count": 28, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df.describe()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# Querying" ] }, { "cell_type": "code", "execution_count": 32, "metadata": { "collapsed": true }, "outputs": [ { "data": { "text/plain": [ "ConnectionID EventID\n", "26 939 45\n", " 940 40\n", " 941 77\n", " 942 40\n", " 943 40\n", " 944 73\n", " 945 105\n", "28 1179 30\n", " 1180 40\n", " 1181 15\n", " 1334 35\n", "29 1191 30\n", " 1201 10\n", " 1229 15\n", " 1274 30\n", " 1306 40\n", " 1328 30\n", " 1331 30\n", "33 1765 10\n", "34 1768 60\n", " 1888 60\n", "37 1982 20\n", " 2071 20\n", " 2101 20\n", " 2212 30\n", " 2348 60\n", "38 2403 5\n", " 2412 20\n", " 2495 20\n", " 2512 10\n", " ... \n", "1377 133744 8\n", " 133956 8\n", " 134026 8\n", " 134555 57\n", " 134887 60\n", "1378 135371 10\n", " 135372 60\n", " 135425 10\n", " 135433 10\n", " 135434 55\n", " 135477 15\n", " 135478 60\n", " 135480 10\n", " 135513 10\n", " 135511 60\n", " 135515 10\n", " 135544 10\n", " 135545 55\n", " 135557 10\n", " 135556 5\n", " 135562 10\n", " 135574 10\n", " 135573 50\n", " 135593 10\n", " 135600 10\n", " 135601 52\n", " 135662 10\n", " 135663 55\n", "1382 139982 10\n", "1383 140171 40\n", "Name: Duration, dtype: int64" ] }, "execution_count": 32, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df.Duration" ] }, { "cell_type": "code", "execution_count": 35, "metadata": { "collapsed": false }, "outputs": [ { "data": { "text/plain": [ "Timestamp 2013-02-20 06:33:00\n", "ExerciseType Anaerobic\n", "Intensity 2\n", "Duration 40\n", "Name: (26, 942), dtype: object" ] }, "execution_count": 35, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df.iloc[3]" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# Plotting" ] }, { "cell_type": "code", "execution_count": 36, "metadata": { "collapsed": false }, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 36, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYEAAAD8CAYAAACRkhiPAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\njhkCktQxQ0CSOvZ/2qNro1UCd3gAAAAASUVORK5CYII=\n", "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "%matplotlib inline\n", "\n", "df.Duration.hist()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# Magic" ] }, { "cell_type": "code", "execution_count": 37, "metadata": { "collapsed": true }, "outputs": [], "source": [ "%qtconsole" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "collapsed": true }, "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": "3.6.0" } }, "nbformat": 4, "nbformat_minor": 2 }