WaterPointDataExchange Descriptive Statistics

This report is for analyizing Water Point Data . This data consists of 452549 records . These are the various water point data uploaded into Water Point Data Exchange across the world .

The information of water point data consists of the location of water source , country name , the water source such as borewell , tap etc , technology with which water is made available , the source who reported the water point , quality of water , and the status of water point i.e whether water was available at the time of reporting.

1. Checking for zero values in the numeric fields . This is done so that if they are important fields , then need to check the reason for zero values.

                Row.ID         X.install_year              X.lat_deg 
                     0                 121876                   2284 
             X.lon_deg                  Count X.fecal_coliform_value 
                  2280                      0                 446417 
             Report.Yr 
                     0

It is shown that 2279 records have zero latitude and longitude values .

Check the details of those records as follows:

 X.status_id.f             X.water_source.f          X.water_tech.f
 no     : 109   Borehole           :869                     :1598  
 unknown: 500   Unknown            :328     Bush Pump Type B: 273  
 yes    :1670   Protected Spring   :306     Bucket Only     : 201  
                Protected Borehole :233     Other           :  47  
                Unprotected River  : 91     Rope and Bucket :  46  
                Protected Deep Well: 64     Bush Pump Type A:  29  
                (Other)            :388     (Other)         :  85  
                                                                         X.source.f  
 Evidence Action                                                              :1598  
 The Zimbabwe Rural Water, Sanitation &  Hygiene Management Information System: 675  
 Water For People                                                             :   3  
 Ministry of Water Resources Sierra Leone                                     :   1  
 Swaziland Department of Water Affairs                                        :   1  
 TEST                                                                         :   1  
 (Other)                                                                      :   0  
 X.country_id.f   X.lat_deg   X.lon_deg   Report.Dt         
 UG     :1599   Min.   :0   Min.   :0   Min.   :2012-09-20  
 ZW     : 675   1st Qu.:0   1st Qu.:0   1st Qu.:2013-01-25  
 BO     :   1   Median :0   Median :0   Median :2013-10-05  
 MW     :   1   Mean   :0   Mean   :0   Mean   :2014-03-29  
 PE     :   1   3rd Qu.:0   3rd Qu.:0   3rd Qu.:2015-04-10  
 SL     :   1   Max.   :0   Max.   :0   Max.   :2017-06-29  
 (Other):   1

2. Water_tech and water_source values need to be cleant . There is no standard value for each type of water source and water technology . This hampers in modelling for prediction of water status and is not informative.

3. How many waterpoints are uploaded by year and how many are of them are functional ? The following graph provides the required information.

The upload of water point records by year shows that it is negatively skewed.

   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
    1.0     3.0    32.0   511.4   238.0 21375.0

Hence displaying the water point records for years that have uploads more than 238 .

4. Distribution of waterpoints by country .

5. Visualizing the distribution on map . This is to display first 1000 water points.

Water points can be clustered further and displayed on the map.

It helps in understanding the proximity of the water points .

6. Water points distribution by Country and the Reporting Year

7. Source of the uploaded water point is a mandatory field. It provides the name of the organization collecting and reporting the data record.

Distribution of water points by the sources and to check many are functional ?

WaterPointDataExchange Descriptive Statistics

Vidya

12 July 2018

This report is for analyizing Water Point Data . This data consists of 452549 records . These are the various water point data uploaded into Water Point Data Exchange across the world .

1. Checking for zero values in the numeric fields . This is done so that if they are important fields , then need to check the reason for zero values.

It is shown that 2279 records have zero latitude and longitude values .

Check the details of those records as follows:

2. Water_tech and water_source values need to be cleant . There is no standard value for each type of water source and water technology . This hampers in modelling for prediction of water status and is not informative.

3. How many waterpoints are uploaded by year and how many are of them are functional ? The following graph provides the required information.

The upload of water point records by year shows that it is negatively skewed.

Hence displaying the water point records for years that have uploads more than 238 .

4. Distribution of waterpoints by country .

5. Visualizing the distribution on map . This is to display first 1000 water points.

Water points can be clustered further and displayed on the map.

It helps in understanding the proximity of the water points .

6. Water points distribution by Country and the Reporting Year

7. Source of the uploaded water point is a mandatory field. It provides the name of the organization collecting and reporting the data record.

Distribution of water points by the sources and to check many are functional ?

WaterPointDataExchange Descriptive Statistics

Vidya

12 July 2018

This report is for analyizing Water Point Data . This data consists of 452549 records . These are the various water point data uploaded into Water Point Data Exchange across the world .

1. Checking for zero values in the numeric fields . This is done so that if they are important fields , then need to check the reason for zero values.

It is shown that 2279 records have zero latitude and longitude values .

Check the details of those records as follows:

2. Water_tech and water_source values need to be cleant . There is no standard value for each type of water source and water technology . This hampers in modelling for prediction of water status and is not informative.

3. How many waterpoints are uploaded by year and how many are of them are functional ? The following graph provides the required information.

The upload of water point records by year shows that it is negatively skewed.

Hence displaying the water point records for years that have uploads more than 238 .

4. Distribution of waterpoints by country .

5. Visualizing the distribution on map . This is to display first 1000 water points.

Water points can be clustered further and displayed on the map.

It helps in understanding the proximity of the water points .

6. Water points distribution by Country and the Reporting Year

7. Source of the uploaded water point is a mandatory field. It provides the name of the organization collecting and reporting the data record.

Distribution of water points by the sources and to check many are functional ?

8. What are the various status descriptions which tells the condition of a waterpoint? Can we understand the most common problems related to non functionality of water point ?