From b26dfba99dfd1e96602a03ea765e0c6692278175 Mon Sep 17 00:00:00 2001
From: Vaibhav Karve <vaibhavskarve@gmail.com>
Date: Sun, 26 Jul 2020 11:42:00 -0500
Subject: [PATCH] add EntriesD.ipynb and LinkSizes.ipynb
---
.../ReadData-checkpoint.ipynb | 35 ++-
ReadData/EntriesD.ipynb | 186 ++++++++++++++++
ReadData/LinkSizes.ipynb | 204 ++++++++++++++++++
3 files changed, 418 insertions(+), 7 deletions(-)
create mode 100644 ReadData/EntriesD.ipynb
create mode 100644 ReadData/LinkSizes.ipynb
diff --git a/ReadData/.ipynb_checkpoints/ReadData-checkpoint.ipynb b/ReadData/.ipynb_checkpoints/ReadData-checkpoint.ipynb
index d3f1f59..1a31605 100644
--- a/ReadData/.ipynb_checkpoints/ReadData-checkpoint.ipynb
+++ b/ReadData/.ipynb_checkpoints/ReadData-checkpoint.ipynb
@@ -12,7 +12,7 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
@@ -23,9 +23,18 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 2,
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "link_id,begin_node_id,end_node_id,begin_angle,end_angle,street_length,osm_name,osm_class,osm_way_id,startX,startY,endX,endY,osm_changeset,birth_timestamp,death_timestamp\n",
+ "\n"
+ ]
+ }
+ ],
"source": [
"## Create a dictionary of links with entries as:\n",
"## (begin_node_id, end_node_id): links_id\n",
@@ -41,9 +50,21 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 4,
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "ename": "FileNotFoundError",
+ "evalue": "[Errno 2] No such file or directory: '../DataFiles/travel_times_2011.csv'",
+ "output_type": "error",
+ "traceback": [
+ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+ "\u001b[0;31mFileNotFoundError\u001b[0m Traceback (most recent call last)",
+ "\u001b[0;32m<ipython-input-4-ddb8c86be344>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m 6\u001b[0m \u001b[0;32mwith\u001b[0m \u001b[0mopen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'../MultiplicativeAlgorithm/D_2011.csv'\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m'w'\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0mwritefile\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 7\u001b[0m \u001b[0mwritefile\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mwrite\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'L,T,traveltime,trips\\n'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 8\u001b[0;31m \u001b[0;32mwith\u001b[0m \u001b[0mopen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'../DataFiles/travel_times_2011.csv'\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0mrawfile\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 9\u001b[0m \u001b[0mprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mrawfile\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mreadline\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 10\u001b[0m \u001b[0mstart_time\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mdt\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdatetime\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mstrptime\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'2011-01-01 00:00:00'\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m'%Y-%m-%d %X'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+ "\u001b[0;31mFileNotFoundError\u001b[0m: [Errno 2] No such file or directory: '../DataFiles/travel_times_2011.csv'"
+ ]
+ }
+ ],
"source": [
"print('This message is a fail-safe. Comment out this line only if you know what you are doing.'); print(failsafe)\n",
"\n",
@@ -115,7 +136,7 @@
"source": [
"## Read from full_link_ids.txt\n",
"\n",
- "with open('../Multiplicative Algorithm/full_link_ids.txt', 'r') as readfile:\n",
+ "with open('../MultiplicativeAlgorithm/full_link_ids.txt', 'r') as readfile:\n",
" full_links = [int(line.strip()) for line in readfile]\n",
" print(len(full_links))"
]
@@ -199,7 +220,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
- "version": "3.6.6"
+ "version": "3.8.3"
}
},
"nbformat": 4,
diff --git a/ReadData/EntriesD.ipynb b/ReadData/EntriesD.ipynb
new file mode 100644
index 0000000..842e0de
--- /dev/null
+++ b/ReadData/EntriesD.ipynb
@@ -0,0 +1,186 @@
+{
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "# Entries in $D$"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "In this notebook, we look at how many numerical entries there are in the $D$ matrix."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 5,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import numpy as np"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 47,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "full_link_ids.txt links.csv README.md\r\n"
+ ]
+ }
+ ],
+ "source": [
+ "ls ../DataFiles/"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 9,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "(8760, 2302)"
+ ]
+ },
+ "execution_count": 9,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "D = np.loadtxt('../MultiplicativeAlgorithm/D_trips.txt')\n",
+ "D.shape"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 39,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "97.25287024584539"
+ ]
+ },
+ "execution_count": 39,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "non_nan = np.count_nonzero(~np.isnan(D.flatten()))\n",
+ "total = D.size\n",
+ "non_nan/total*100"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 42,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "20165520"
+ ]
+ },
+ "execution_count": 42,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "total"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 15,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "D2 = D.flatten()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 27,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "x = D2[98]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 33,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "True"
+ ]
+ },
+ "execution_count": 33,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "np.isnan(x)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 44,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "3548011030.0"
+ ]
+ },
+ "execution_count": 44,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "np.nansum(D2)"
+ ]
+ }
+ ],
+ "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": "3.8.3"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}
diff --git a/ReadData/LinkSizes.ipynb b/ReadData/LinkSizes.ipynb
new file mode 100644
index 0000000..2979a55
--- /dev/null
+++ b/ReadData/LinkSizes.ipynb
@@ -0,0 +1,204 @@
+{
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "# Link sizes"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## This notebook computes the average sizes of all links in our dataset."
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "We read *links.csv*. This file contains data for all links (including links with missing entries)."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 1,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import csv\n",
+ "import statistics"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 2,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "{0: 'link_id',\n",
+ " 1: 'begin_node_id',\n",
+ " 2: 'end_node_id',\n",
+ " 3: 'begin_angle',\n",
+ " 4: 'end_angle',\n",
+ " 5: 'street_length',\n",
+ " 6: 'osm_name',\n",
+ " 7: 'osm_class',\n",
+ " 8: 'osm_way_id',\n",
+ " 9: 'startX',\n",
+ " 10: 'startY',\n",
+ " 11: 'endX',\n",
+ " 12: 'endY',\n",
+ " 13: 'osm_changeset',\n",
+ " 14: 'birth_timestamp',\n",
+ " 15: 'death_timestamp'}"
+ ]
+ },
+ "execution_count": 2,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "with open('../DataFiles/links.csv', 'r') as csvfile:\n",
+ " reader = csv.reader(csvfile)\n",
+ " header, *data = list(reader)\n",
+ "\n",
+ "dict(enumerate(header))"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "---"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "We are interested in entry #5 i.e. `street_length`"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 14,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Mean = 132.98258543251998\n",
+ "Median = 95.569\n",
+ "Mode = 79.259\n",
+ "Std.Dev = 107.84111322501701\n",
+ "Minimum = 2.806\n",
+ "Maximum = 3937.115\n",
+ "Total = 260855\n"
+ ]
+ }
+ ],
+ "source": [
+ "street_lengths = [row[5] for row in data]\n",
+ "street_lengths = list(map(float, street_lengths)) # str -> float\n",
+ "print('Mean =', statistics.mean(street_lengths))\n",
+ "print('Median =', statistics.median(street_lengths))\n",
+ "print('Mode =', statistics.mode(street_lengths))\n",
+ "print('Std.Dev =', statistics.stdev(street_lengths))\n",
+ "print('Minimum =', min(street_lengths))\n",
+ "print('Maximum =', max(street_lengths))\n",
+ "print('Total =', len(street_lengths))"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "---"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "We now read data for only the 2302 links we have chosen for our analysis."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 7,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "with open('../DataFiles/full_link_ids.txt', 'r') as txtfile:\n",
+ " link_ids = [line.strip() for line in txtfile.readlines()]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 11,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "full_links = [row for row in data if row[0] in link_ids]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 15,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Mean = 106.40565682015638\n",
+ "Median = 79.981\n",
+ "Mode = 78.523\n",
+ "Std.Dev = 133.08834141783507\n",
+ "Minimum = 40.005\n",
+ "Maximum = 2676.248\n",
+ "Total = 2302\n"
+ ]
+ }
+ ],
+ "source": [
+ "street_lengths = [row[5] for row in full_links]\n",
+ "street_lengths = list(map(float, street_lengths)) # str -> float\n",
+ "print('Mean =', statistics.mean(street_lengths))\n",
+ "print('Median =', statistics.median(street_lengths))\n",
+ "print('Mode =', statistics.mode(street_lengths))\n",
+ "print('Std.Dev =', statistics.stdev(street_lengths))\n",
+ "print('Minimum =', min(street_lengths))\n",
+ "print('Maximum =', max(street_lengths))\n",
+ "print('Total =', len(street_lengths))"
+ ]
+ }
+ ],
+ "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": "3.8.3"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}
--
GitLab