Difference between revisions of "ISSS608 2017-18 T3 Assignment LIU YUQING Data Preparation"

From Visual Analytics and Applications
Jump to navigation Jump to search
 
(3 intermediate revisions by the same user not shown)
Line 27: Line 27:
 
=Dataset description=
 
=Dataset description=
 
Mini-Challenge 2 provides two datasets - [Boonsong Lekagul waterways readings.csv] and [chemical units of measure.csv] and one map image about rivers and streams of some specific locations.
 
Mini-Challenge 2 provides two datasets - [Boonsong Lekagul waterways readings.csv] and [chemical units of measure.csv] and one map image about rivers and streams of some specific locations.
−
[Boonsong Lekagul waterways readings.csv] includes 5 variables: ID, measure, value of masure, location and measuring date. There are 10 locations, 106 measures and measuring date span is from 1998 to 2016.
+
 
 +
[Boonsong Lekagul waterways readings.csv] includes 5 variables: ID, measure, value of measure, location and measuring date. There are 10 locations, 106 measures and measuring date span is from 1998 to 2016.
 +
 
 
[chemical units of measure.csv] includes measures and unit of each measure.
 
[chemical units of measure.csv] includes measures and unit of each measure.
  
 
=Map view=
 
=Map view=
−
According to the map image, we can observe geographical distribution of locations, in order to get specific coordinates of each location, we add the image into tableau as background and set basic range of coordinates of X axis and Y axis given by Mini-Challenge 2.
+
According to the map image, we can observe the geographical distribution of locations, in order to get specific coordinates of each location, we add the image into tableau as background and set basic range of coordinates of X axis and Y axis given by Mini-Challenge 2.
−
[[Image:image1-1.jpg|800px|center]]
+
 
−
Here we added point as annotate on the top of each arrow of each location, so X&Y coordinates of each location will show on the map. We do same for all other locations and we get the [Location.xlsx] file about coordinates of each location.  
+
[[Image:image1-1.jpg|400px]]
−
[[Image:image1-2.jpg|500px|center]]
+
 
 +
Here we added pints as annotate on the top of each arrow of each location, so X&Y coordinates of each location will show on the map. We do same for all other locations and we get the [Location.xlsx] file about coordinates of each location.  
 +
 
 +
[[Image:image1-2.jpg|200px]]
  
 
=Data augmentation and data pruning=
 
=Data augmentation and data pruning=
−
After overview of whole data, we observed value variance among measures are quite big, and measuring time span of each measure also varies greatly. Units of measures are mainly separated into ug/l and mg/l, it’s hard for us to estimate whether the value of this chemical is toxic for water or not. In this case, I found a file from the California Water Board as reference.
+
After the overview of whole data, we observed value variance among measures are quite big and measuring time span of each measure also varies greatly. Units of measures are mainly separated into ug/l and mg/l, it’s hard for us to estimate whether the value of this chemical is toxic for water or not. In this case, I found a file from the California Water Board as a reference.
−
[[Image:image1-3.jpg|800px|center]]
+
 
 +
[[Image:image1-3.jpg|800px]]
 +
 
 
This file provides MCL(California’s maximum contaminant levels) and DLR( Detection limits for purpose of reporting) of about 120 measures for regulated drinking water. Maximum level of contaminants in drinking water should be lower than raw water, so any value of chemical less than its corresponding level could be considered insignificant.  
 
This file provides MCL(California’s maximum contaminant levels) and DLR( Detection limits for purpose of reporting) of about 120 measures for regulated drinking water. Maximum level of contaminants in drinking water should be lower than raw water, so any value of chemical less than its corresponding level could be considered insignificant.  
 
<br>
 
<br>
Line 50: Line 57:
 
1. Compare measures of Boonsong Lekagul waterways readings with measures given in California Water Board. Check measures one by one of both dataset, selected common measures of both. There are 25 measures appeared in CWB in total. Saved the 25 measures in [Measures with MCL] file
 
1. Compare measures of Boonsong Lekagul waterways readings with measures given in California Water Board. Check measures one by one of both dataset, selected common measures of both. There are 25 measures appeared in CWB in total. Saved the 25 measures in [Measures with MCL] file
  
−
2. Unify units of MCL value to standard unit of these 25 measures, for measures with unit ug/l, changed the maximum value in CWB as ug/l for comparison.
+
2. Unify units of MCL value to a standard unit of these 25 measures, for measures with unit ug/l, changed the maximum value in CWB as ug/l for comparison.
  
 
3. Join [Measures with MCL] table to [Boonsong Lekagul waterways readings] table in JMP using left outer join so that measures not contained in CWS can also be reserved. We saved the joined data as excel file.
 
3. Join [Measures with MCL] table to [Boonsong Lekagul waterways readings] table in JMP using left outer join so that measures not contained in CWS can also be reserved. We saved the joined data as excel file.
−
[[Image:image1-4.jpg|500px|center]]
 
−
'''Join table with MCL level'''
 
−
[[Image:image1-5.jpg|500px|center]]
 
−
Compare value of these measures in excel, for those lower than MCL level, delete the datapoints, others all stay same. Using if function: =IF(B:B<G:G,"null",B:B), column B is measured value, column G is MCL level, after calculation, data file looks like below:
 
−
==Step by Step Discription==
 
−
[[Image:image1-6.jpg|500px|center]]
 
−
We deleted all records with “null” value. After data cleaning, 13 measures all cleaned, which means their value are all lower than MCL level over the date, they are:
 
−
 
−
1,2,4-Trichlorobenzene 2008 – 2009, Aldrin, Alachlor, Aluminium, Barium, Berilium, Endrin, Hexachlorobenzene, Mercury, Methoxychlor, Pentachlorobenzene, Selenium,Simazine.
 
  
−
Now data records are 110,581 and we save the remain data as [Measures exclude nonimpact] file.
+
'''Join table'''
−
 
 
−
===Exclude misleading records===
 
 
<table cellspacing="10" border="1">
 
<table cellspacing="10" border="1">
 
<tr>
 
<tr>
 
<td>  
 
<td>  
−
Exclusion criterion:
+
'''Join table with MCL level'''
−
 
+
<td>[[Image:image1-4.jpg|700px|right]]</td>
−
(1) id without full movement records( all visitors should come in and get out from both entrances so those ids that only have one entrance should be excluded).
 
−
 
 
−
(2)id without full timestamp records.( those id without the come in and get out records).
 
−
 
 
−
(3) repeat records
 
−
<td>[[File:Entrances number2.PNG|700px|right]]</td>
 
 
</tr>
 
</tr>
 
</table>
 
</table>
  
−
===Extract the car sequences===
+
'''Compare with MCL level'''
 
<table cellspacing="10" border="1">
 
<table cellspacing="10" border="1">
 
<tr>
 
<tr>
−
<td> The most essentail step for data preparation is to extract the car sequences which helps to summary the life patterns. This step is conducted in JMP with the function[Col Rank(Timestamp,car-id)]
+
<td>  
−
<td>[[File:Car sequences.PNG|800px|right]]</td>
+
Compare the value of these measures in excel, for those lower than the MCL level, delete the data points, others all stay same.  
 +
<td>
 +
[[Image:image1-5.jpg|700px|right]]</td>
 
</tr>
 
</tr>
 
</table>
 
</table>
−
===Label vehicles in their movement order and then create Episode based on the movement order and id===
+
 
 +
'''Select value < MCL level'''
 
<table cellspacing="10" border="1">
 
<table cellspacing="10" border="1">
 
<tr>
 
<tr>
−
<td> Number the movement order for each car-id and then list the car-id with episode.
+
<td>  
−
 
+
Using if function: =IF(B:B<G:G,"null",B:B), column B is measured value, column G is MCL level, after calculation, here is the data file:
−
Level: The order of movement(entrance---gate ：level of entrance is one and the level of gate is two)
+
<td>
−
 
+
[[Image:image1-6.jpg|700px|right]]</td>
−
Episode: Each entrance & exit is one episode, so normally each id should has only one episode.
 
−
<td>[[File:Level_and_eposide.PNG|800px|right]]</td>
 
 
</tr>
 
</tr>
 
</table>
 
</table>
  
−
===Compute the last duration, camping hour and single checkpoint duration===
+
'''Data cleaning'''
 
<table cellspacing="10" border="1">
 
<table cellspacing="10" border="1">
 
<tr>
 
<tr>
−
<td> Compute the multipul duration in excel for better visualization.Last duration(day),camping hour(hour),single checkpoint duration(min)
+
<td>  
−
<td>[[File:Camping hour.PNG|800px|right]]</td>
+
We deleted all records with “null” value. After data cleaning, 13 measures all cleaned, which means their value are all lower than MCL level over the date, they are:
 +
 
 +
1,2,4-Trichlorobenzene 2008 – 2009, Aldrin, Alachlor, Aluminium, Barium, Berilium, Endrin, Hexachlorobenzene, Mercury, Methoxychlor, Pentachlorobenzene, Selenium,Simazine.
 +
<td>
 +
[[Image:image1-7.jpg|500px|right]]</td>
 
</tr>
 
</tr>
 
</table>
 
</table>
  
−
===Coordinates Extractation and Preparation for Gephi===
+
There are 106 chemicals in total.
−
<table cellspacing="10" border="1">
+
 
−
<tr>
+
25 of them have standard MCL value.
−
<td> Extract the coordinates in tableau and then prepare the coordinates for Gephi visualization
+
 
−
<td>[[File:Gephi.PNG|600px|right]]</td>
+
12 of chemicals less than MCL over the years.
−
</tr>
 
−
</table>
 
  
−
===Participent Segamentation===
+
Now data records are 110,581 and we save the remaining data as [Measures exclude nonimpact] file.
−
<table cellspacing="10" border="1">
 
−
<tr>
 
−
<td> All the participents are classified into Camper,No-camper and Ranger
 
−
<td>[[File:Visitors type.PNG|700px|right]]</td>
 
−
</tr>
 
−
</table>
 

Latest revision as of 02:23, 8 July 2018

Header.jpg ISSS608 Visual Analytics and Applications_Vast Challenge_Mini Challenge2

Background

Data Preparation

Analysis & Insights

Comments & References

 


Dataset description

Mini-Challenge 2 provides two datasets - [Boonsong Lekagul waterways readings.csv] and [chemical units of measure.csv] and one map image about rivers and streams of some specific locations.

[Boonsong Lekagul waterways readings.csv] includes 5 variables: ID, measure, value of measure, location and measuring date. There are 10 locations, 106 measures and measuring date span is from 1998 to 2016.

[chemical units of measure.csv] includes measures and unit of each measure.

Map view

According to the map image, we can observe the geographical distribution of locations, in order to get specific coordinates of each location, we add the image into tableau as background and set basic range of coordinates of X axis and Y axis given by Mini-Challenge 2.

Image1-1.jpg

Here we added pints as annotate on the top of each arrow of each location, so X&Y coordinates of each location will show on the map. We do same for all other locations and we get the [Location.xlsx] file about coordinates of each location.

Image1-2.jpg

Data augmentation and data pruning

After the overview of whole data, we observed value variance among measures are quite big and measuring time span of each measure also varies greatly. Units of measures are mainly separated into ug/l and mg/l, it’s hard for us to estimate whether the value of this chemical is toxic for water or not. In this case, I found a file from the California Water Board as a reference.

Image1-3.jpg

This file provides MCL(California’s maximum contaminant levels) and DLR( Detection limits for purpose of reporting) of about 120 measures for regulated drinking water. Maximum level of contaminants in drinking water should be lower than raw water, so any value of chemical less than its corresponding level could be considered insignificant.
Notice: all units are mg/l in this file.

Data cleaning

Steps:

1. Compare measures of Boonsong Lekagul waterways readings with measures given in California Water Board. Check measures one by one of both dataset, selected common measures of both. There are 25 measures appeared in CWB in total. Saved the 25 measures in [Measures with MCL] file

2. Unify units of MCL value to a standard unit of these 25 measures, for measures with unit ug/l, changed the maximum value in CWB as ug/l for comparison.

3. Join [Measures with MCL] table to [Boonsong Lekagul waterways readings] table in JMP using left outer join so that measures not contained in CWS can also be reserved. We saved the joined data as excel file.

Join table

Join table with MCL level

Image1-4.jpg

Compare with MCL level

Compare the value of these measures in excel, for those lower than the MCL level, delete the data points, others all stay same.

Image1-5.jpg

Select value < MCL level

Using if function: =IF(B:B<G:G,"null",B:B), column B is measured value, column G is MCL level, after calculation, here is the data file:

Image1-6.jpg

Data cleaning

We deleted all records with “null” value. After data cleaning, 13 measures all cleaned, which means their value are all lower than MCL level over the date, they are:

1,2,4-Trichlorobenzene 2008 – 2009, Aldrin, Alachlor, Aluminium, Barium, Berilium, Endrin, Hexachlorobenzene, Mercury, Methoxychlor, Pentachlorobenzene, Selenium,Simazine.

Image1-7.jpg

There are 106 chemicals in total.

25 of them have standard MCL value.

12 of chemicals less than MCL over the years.

Now data records are 110,581 and we save the remaining data as [Measures exclude nonimpact] file.

Retrieved from ‘https://wiki.smu.edu.sg/1718t3isss608/index.php?title=ISSS608_2017-18_T3_Assignment_LIU_YUQING_Data_Preparation&oldid=5070’