Data Analytics and Computational Social Science: Brinda Murulidhara HW4

Brinda Murulidhara

Read in a dataset

I have chosen the Emergency - 911 calls dataset from Kaggle (https://www.kaggle.com/mchirico/montcoalert/version/32) for my final project. The dataset contains emergency 911 calls in Montgomery County, Pennsylvania from 2015 to 2020. Below is the code snippet to read and preview the data.

library(dplyr)
emergency_calls_data <- read.csv("911.csv")
head(emergency_calls_data)

       lat       lng
1 40.29788 -75.58129
2 40.25806 -75.26468
3 40.12118 -75.35198
4 40.11615 -75.34351
5 40.25149 -75.60335
6 40.25347 -75.28324
                                                                                 desc
1           REINDEER CT & DEAD END;  NEW HANOVER; Station 332; 2015-12-10 @ 17:10:52;
2 BRIAR PATH & WHITEMARSH LN;  HATFIELD TOWNSHIP; Station 345; 2015-12-10 @ 17:29:21;
3                          HAWS AVE; NORRISTOWN; 2015-12-10 @ 14:39:21-Station:STA27;
4               AIRY ST & SWEDE ST;  NORRISTOWN; Station 308A; 2015-12-10 @ 16:47:36;
5    CHERRYWOOD CT & DEAD END;  LOWER POTTSGROVE; Station 329; 2015-12-10 @ 16:56:52;
6               CANNON AVE & W 9TH ST;  LANSDALE; Station 345; 2015-12-10 @ 15:39:04;
    zip                   title           timeStamp               twp
1 19525  EMS: BACK PAINS/INJURY 2015-12-10 17:10:52       NEW HANOVER
2 19446 EMS: DIABETIC EMERGENCY 2015-12-10 17:29:21 HATFIELD TOWNSHIP
3 19401     Fire: GAS-ODOR/LEAK 2015-12-10 14:39:21        NORRISTOWN
4 19401  EMS: CARDIAC EMERGENCY 2015-12-10 16:47:36        NORRISTOWN
5    NA          EMS: DIZZINESS 2015-12-10 16:56:52  LOWER POTTSGROVE
6 19446        EMS: HEAD INJURY 2015-12-10 15:39:04          LANSDALE
                        addr e
1     REINDEER CT & DEAD END 1
2 BRIAR PATH & WHITEMARSH LN 1
3                   HAWS AVE 1
4         AIRY ST & SWEDE ST 1
5   CHERRYWOOD CT & DEAD END 1
6      CANNON AVE & W 9TH ST 1

Descriptive statistics

Mean

Below are the means of latitude and longitude columns.

summarise(emergency_calls_data, mean_latitude=mean(lat), mean_longitude=mean(lng))

  mean_latitude mean_longitude
1      40.15816       -75.3001

Median

Below are the medians of latitude and longitude columns.

summarise(emergency_calls_data, median_latitude=median(lat), median_longitude=median(lng))

  median_latitude median_longitude
1        40.14393        -75.30514

Standard Deviation

Below are the standard deviations of latitude and longitude columns.

summarise(emergency_calls_data, sd_latitude=sd(lat), sd_longitude=sd(lng))

  sd_latitude sd_longitude
1   0.2206414     1.672884

Frequencies

Below are the frequencies of zipcodes (zip), emergency sub categories (title) and townships (twp).

emergency_calls_data %>%
  count(zip)

      zip     n
1    1104     1
2    3103     2
3    3366     1
4    7081     1
5    7203     1
6    7726     1
7    8033     1
8    8065     1
9    8077     1
10   8361     4
11   8502     1
12   8628     3
13   8832     4
14  15090     1
15  15301     2
16  17331     4
17  17506     1
18  17507     1
19  17545     3
20  17555     1
21  17566     1
22  17603     2
23  17752     3
24  17810     1
25  17901     1
26  18011     1
27  18036    15
28  18040     1
29  18041  2678
30  18042     1
31  18049     1
32  18051     1
33  18054  2282
34  18056    50
35  18070   453
36  18073  4849
37  18074  2996
38  18076  2028
39  18080     1
40  18092    69
41  18101     7
42  18102     1
43  18103     4
44  18104     2
45  18901     4
46  18902     2
47  18911     1
48  18914   286
49  18915   768
50  18927     5
51  18932    67
52  18936  1684
53  18938     1
54  18940     3
55  18944    16
56  18951    66
57  18958     9
58  18960   183
59  18964  8569
60  18966   227
61  18969  4853
62  18974  1472
63  18976   297
64  19001 10113
65  19002 21070
66  19003  7283
67  19004  8114
68  19006 14794
69  19008     2
70  19009   371
71  19010  8624
72  19012  3941
73  19018     1
74  19020    11
75  19021     4
76  19023     1
77  19025  3475
78  19026     2
79  19027 12288
80  19030     2
81  19031  4196
82  19034  6302
83  19035  3212
84  19038 17318
85  19040 13568
86  19041  3244
87  19044  9869
88  19046 17886
89  19047     1
90  19050     2
91  19053    46
92  19054     1
93  19057     3
94  19063     3
95  19064     1
96  19066  3049
97  19070     1
98  19072  4673
99  19073     1
100 19075  2331
101 19082    15
102 19083   169
103 19085  1832
104 19087  2373
105 19090 17377
106 19095  7118
107 19096  7456
108 19102     1
109 19103     1
110 19104     1
111 19106     6
112 19107    12
113 19111   164
114 19115    36
115 19116    22
116 19118   314
117 19119    11
118 19120   162
119 19121     2
120 19122     1
121 19124     1
122 19126   197
123 19127     4
124 19128   929
125 19129     5
126 19131   955
127 19134     1
128 19135     1
129 19138    27
130 19139     2
131 19140     1
132 19144     4
133 19147     2
134 19150  2024
135 19151  1875
136 19153     2
137 19301     7
138 19310     1
139 19312     2
140 19320     1
141 19333     5
142 19341     5
143 19348     8
144 19355    22
145 19365     1
146 19380    14
147 19382     8
148 19390     3
149 19401 45606
150 19403 34888
151 19404     5
152 19405  3054
153 19406 22464
154 19422 12785
155 19423    25
156 19425     6
157 19426 16436
158 19428 14574
159 19435   277
160 19437     2
161 19438 14425
162 19440  8377
163 19443     4
164 19444  7177
165 19445     1
166 19446 32270
167 19450     1
168 19453   680
169 19454 17661
170 19456     1
171 19457     1
172 19460  3006
173 19462 13264
174 19464 43910
175 19465  3133
176 19468 18939
177 19472    49
178 19473  7412
179 19474    24
180 19475   402
181 19477    60
182 19486     5
183 19490    15
184 19492   639
185 19503    23
186 19504   628
187 19505   158
188 19512  1426
189 19518   486
190 19520     5
191 19525  5997
192 19543     1
193 19545     1
194 19601    13
195 19602     1
196 19604     1
197 19605     2
198 19607     1
199 19609     9
200 19610     8
201 21701     2
202 23005     2
203 36107     1
204 77316     1
205    NA 80199

emergency_calls_data %>%
  count(title)

                                   title      n
1                   EMS: ABDOMINAL PAINS   9005
2                    EMS: ACTIVE SHOOTER      3
3                 EMS: ALLERGIC REACTION   2878
4             EMS: ALTERED MENTAL STATUS  10088
5                        EMS: AMPUTATION     99
6                       EMS: ANIMAL BITE    583
7                    EMS: APPLIANCE FIRE     46
8                     EMS: ARMED SUBJECT      2
9                    EMS: ASSAULT VICTIM   4199
10                EMS: BACK PAINS/INJURY   4880
11               EMS: BARRICADED SUBJECT      2
12                EMS: BOMB DEVICE FOUND     10
13                      EMS: BOMB THREAT      2
14                    EMS: BUILDING FIRE   1323
15                      EMS: BURN VICTIM    272
16         EMS: CARBON MONOXIDE DETECTOR    458
17                   EMS: CARDIAC ARREST   5443
18                EMS: CARDIAC EMERGENCY  32332
19                          EMS: CHOKING   1220
20                       EMS: CVA/STROKE   8277
21         EMS: DEBRIS/FLUIDS ON HIGHWAY      5
22                      EMS: DEHYDRATION   1559
23               EMS: DIABETIC EMERGENCY   5742
24                 EMS: DISABLED VEHICLE      1
25                        EMS: DIZZINESS   5154
26                         EMS: DROWNING     32
27          EMS: ELECTRICAL FIRE OUTSIDE     27
28                    EMS: ELECTROCUTION     32
29               EMS: ELEVATOR EMERGENCY     29
30              EMS: EMS SPECIAL SERVICE   1448
31                       EMS: EYE INJURY    286
32                      EMS: FALL VICTIM  34676
33                            EMS: FEVER   3364
34                       EMS: FIRE ALARM    116
35               EMS: FIRE INVESTIGATION    111
36               EMS: FIRE POLICE NEEDED      5
37             EMS: FIRE SPECIAL SERVICE    274
38                         EMS: FRACTURE   4094
39                    EMS: GAS-ODOR/LEAK    262
40                 EMS: GENERAL WEAKNESS  11867
41     EMS: HAZARDOUS MATERIALS INCIDENT     50
42                      EMS: HEAD INJURY  18301
43                  EMS: HEAT EXHAUSTION    332
44                     EMS: HEMORRHAGING   8256
45                        EMS: HIT + RUN      1
46              EMS: INDUSTRIAL ACCIDENT     38
47                      EMS: LACERATIONS   2871
48                        EMS: MATERNITY    982
49              EMS: MEDICAL ALERT ALARM  10394
50                  EMS: NAUSEA/VOMITING   7808
51                         EMS: OVERDOSE   8361
52                      EMS: PLANE CRASH      6
53                        EMS: POISONING    224
54               EMS: POLICE INFORMATION      1
55                   EMS: PUBLIC SERVICE      5
56                EMS: RESCUE - ELEVATOR     22
57                 EMS: RESCUE - GENERAL    320
58               EMS: RESCUE - TECHNICAL     37
59                   EMS: RESCUE - WATER    282
60            EMS: RESPIRATORY EMERGENCY  34248
61        EMS: S/B AT HELICOPTER LANDING     74
62                         EMS: SEIZURES  10823
63                         EMS: SHOOTING    237
64                         EMS: STABBING    213
65           EMS: STANDBY FOR ANOTHER CO     10
66                  EMS: SUBJECT IN PAIN  19646
67                   EMS: SUICIDE THREAT      2
68                       EMS: SUSPICIOUS      5
69                 EMS: SYNCOPAL EPISODE  10806
70                      EMS: TRAIN CRASH     10
71                 EMS: TRANSFERRED CALL     43
72              EMS: TRASH/DUMPSTER FIRE      8
73              EMS: UNCONSCIOUS SUBJECT   8791
74        EMS: UNKNOWN MEDICAL EMERGENCY  10698
75                EMS: UNKNOWN TYPE FIRE     16
76             EMS: UNRESPONSIVE SUBJECT   2798
77                 EMS: VEHICLE ACCIDENT  25513
78                     EMS: VEHICLE FIRE    226
79             EMS: VEHICLE LEAKING FUEL      1
80                  EMS: WARRANT SERVICE      8
81                 EMS: WOODS/FIELD FIRE     19
82                Fire: ANIMAL COMPLAINT      1
83                  Fire: APPLIANCE FIRE   1217
84              Fire: BARRICADED SUBJECT      1
85                   Fire: BUILDING FIRE   4754
86                     Fire: BURN VICTIM    227
87        Fire: CARBON MONOXIDE DETECTOR   3990
88                  Fire: CARDIAC ARREST   1364
89               Fire: CARDIAC EMERGENCY      7
90                      Fire: CVA/STROKE      1
91        Fire: DEBRIS/FLUIDS ON HIGHWAY    256
92              Fire: DIABETIC EMERGENCY      1
93                Fire: DISABLED VEHICLE      7
94                       Fire: DIZZINESS      1
95         Fire: ELECTRICAL FIRE OUTSIDE   5111
96              Fire: ELEVATOR EMERGENCY    920
97             Fire: EMS SPECIAL SERVICE      8
98                     Fire: FALL VICTIM      7
99                      Fire: FIRE ALARM  38336
100             Fire: FIRE INVESTIGATION   9444
101             Fire: FIRE POLICE NEEDED   1587
102           Fire: FIRE SPECIAL SERVICE   4050
103                    Fire: FOOT PATROL      1
104                  Fire: GAS-ODOR/LEAK   6740
105               Fire: GENERAL WEAKNESS      1
106   Fire: HAZARDOUS MATERIALS INCIDENT     51
107      Fire: HAZARDOUS ROAD CONDITIONS      2
108                    Fire: HEAD INJURY      3
109                   Fire: HEMORRHAGING      1
110            Fire: MEDICAL ALERT ALARM      5
111                Fire: NAUSEA/VOMITING      2
112                       Fire: OVERDOSE      6
113                    Fire: PLANE CRASH      5
114                      Fire: POISONING      1
115             Fire: POLICE INFORMATION      3
116            Fire: PRISONER IN CUSTODY      1
117                 Fire: PUBLIC SERVICE      1
118                    Fire: PUMP DETAIL    171
119              Fire: RESCUE - ELEVATOR    736
120               Fire: RESCUE - GENERAL    376
121             Fire: RESCUE - TECHNICAL     49
122                 Fire: RESCUE - WATER    295
123          Fire: RESPIRATORY EMERGENCY      2
124               Fire: ROAD OBSTRUCTION      2
125      Fire: S/B AT HELICOPTER LANDING    658
126         Fire: STANDBY FOR ANOTHER CO     12
127                Fire: SUBJECT IN PAIN      4
128                Fire: SUICIDE ATTEMPT      2
129                     Fire: SUSPICIOUS      1
130               Fire: SYNCOPAL EPISODE      3
131                    Fire: TRAIN CRASH     14
132               Fire: TRANSFERRED CALL    102
133            Fire: TRASH/DUMPSTER FIRE   1190
134            Fire: UNCONSCIOUS SUBJECT      4
135      Fire: UNKNOWN MEDICAL EMERGENCY      2
136              Fire: UNKNOWN TYPE FIRE   1964
137           Fire: UNRESPONSIVE SUBJECT      3
138               Fire: VEHICLE ACCIDENT  10864
139                   Fire: VEHICLE FIRE   3232
140           Fire: VEHICLE LEAKING FUEL    337
141               Fire: WOODS/FIELD FIRE   2486
142  Traffic: DEBRIS/FLUIDS ON HIGHWAY -    201
143          Traffic: DISABLED VEHICLE -  47909
144 Traffic: HAZARDOUS ROAD CONDITIONS -   6833
145          Traffic: ROAD OBSTRUCTION -  23235
146          Traffic: VEHICLE ACCIDENT - 148372
147              Traffic: VEHICLE FIRE -   3366
148      Traffic: VEHICLE LEAKING FUEL -    292

emergency_calls_data %>%
  count(twp)

                 twp     n
1                      293
2           ABINGTON 39947
3             AMBLER  4454
4       BERKS COUNTY  1930
5         BRIDGEPORT  3695
6         BRYN ATHYN  1254
7       BUCKS COUNTY  1982
8         CHELTENHAM 30574
9     CHESTER COUNTY  7362
10      COLLEGEVILLE  2916
11      CONSHOHOCKEN  5655
12   DELAWARE COUNTY  1802
13          DOUGLASS  5550
14   EAST GREENVILLE  1316
15     EAST NORRITON 13963
16         FRANCONIA  9297
17        GREEN LANE   385
18           HATBORO  5448
19     HATFIELD BORO  1370
20 HATFIELD TOWNSHIP 11641
21           HORSHAM 18380
22        JENKINTOWN  4150
23          LANSDALE 11963
24     LEHIGH COUNTY   190
25          LIMERICK 14338
26   LOWER FREDERICK  2081
27     LOWER GWYNEDD 11139
28      LOWER MERION 55490
29    LOWER MORELAND 10988
30  LOWER POTTSGROVE 10775
31  LOWER PROVIDENCE 22476
32     LOWER SALFORD  9218
33       MARLBOROUGH  2144
34        MONTGOMERY 17315
35          NARBERTH  1751
36       NEW HANOVER  5207
37        NORRISTOWN 37633
38       NORTH WALES  2182
39         PENNSBURG  2615
40         PERKIOMEN  3141
41      PHILA COUNTY   267
42          PLYMOUTH 20116
43         POTTSTOWN 27387
44          RED HILL  1987
45         ROCKLEDGE  1569
46        ROYERSFORD  3545
47           SALFORD  1488
48     SCHWENKSVILLE  1337
49          SKIPPACK  5513
50         SOUDERTON  3012
51       SPRINGFIELD 15504
52           TELFORD  3376
53        TOWAMENCIN 11407
54            TRAPPE  1736
55      UPPER DUBLIN 18862
56   UPPER FREDERICK  2357
57     UPPER GWYNEDD  8860
58     UPPER HANOVER  3878
59      UPPER MERION 36010
60    UPPER MORELAND 22932
61  UPPER POTTSGROVE  3557
62  UPPER PROVIDENCE 16122
63     UPPER SALFORD  1913
64 WEST CONSHOHOCKEN  5216
65     WEST NORRITON 11187
66   WEST POTTSGROVE  3103
67        WHITEMARSH 17754
68          WHITPAIN 13480
69         WORCESTER  6037

Median latitude and longitude grouped by township

emergency_calls_data %>%
  group_by(twp) %>%
  summarise(median_latitude=median(lat), median_longitude=median(lng))

# A tibble: 69 x 3
   twp              median_latitude median_longitude
   <chr>                      <dbl>            <dbl>
 1 ""                          40.2            -75.4
 2 "ABINGTON"                  40.1            -75.1
 3 "AMBLER"                    40.2            -75.2
 4 "BERKS COUNTY"              40.3            -75.6
 5 "BRIDGEPORT"                40.1            -75.3
 6 "BRYN ATHYN"                40.1            -75.1
 7 "BUCKS COUNTY"              40.2            -75.3
 8 "CHELTENHAM"                40.1            -75.1
 9 "CHESTER COUNTY"            40.2            -75.5
10 "COLLEGEVILLE"              40.2            -75.5
# ... with 59 more rows

Univariate visualisation

Explanation

Below is a plot of emergency subcategory (title) vs frequency of occurrence.
This visualization helps us understand what kind of emergencies occur more frequently in Montgomery County. The emergency response team can make better preparations with this knowledge.
We can conclude that vehicle accidents contribute the most to emergency calls in Montgomery County.

Limitations

This visualization does not aid us in finding the distribution of emergency calls across townships. This is an important piece of information in making preparations for emergencies as some townships may get larger number of calls related to vehicle accidents while others may get more calls regarding stabbing and shooting.
The number of emergency sub categories is large and the distinction between every one of those may be unclear to a naive viewer. It might be good to have a high level view of the emergency categories (E.g. EMS, Traffic, Fire) first and then drill down to the sub categories.
I would include township variable and broad emergency categories (E.g. EMS, Traffic, Fire) in further visualizations to improve my project.

library(ggplot2)
ggplot(emergency_calls_data, aes(x = title)) +
        geom_bar() + 
        theme(axis.text.x=element_text(angle=90, size = 3))

Bivariate Visualisation

Explanation

Below is a plot of township (twp) vs frequency of occurrence grouped by emergency subcategory (title) for a sample of 50 rows.
This visualization helps us understand what kind of emergencies occur more frequently in every township in Montgomery County. It also helps us compare the number of emergencies that occur across townships. The emergency response team can focus its efforts more on townships that have higher counts of emergencies.
We can conclude that Lower Merion has the highest number of emergencies from the sample.

Limitations

This visualization does not consider the entire dataset as it’s built only on a sample of rows. This may not give us a complete representation of the entire dataset.
This visualization does not aid in comparing the trends in emergency calls across years or months.
The number of emergency sub categories is large and the distinction between every one of those may be unclear to a naive viewer. It might be good to have a high level view of the emergency categories (E.g. EMS, Traffic, Fire) first and then drill down to the sub categories.
I would include broad emergency categories (E.g. EMS, Traffic, Fire) and timestamps(year, month etc.) in further visualizations to improve my project. I would also see if it’s possible to group multiple geographically close counties into regions to avoid overwhelming a naive viewer with tens of counties in one visualization.

set.seed(1)  
emergency_calls_data[sample(nrow(emergency_calls_data), 50), ] %>%
ggplot(aes(x = twp, 
           fill = title)) + 
  geom_bar(position = "stack") + 
  theme(axis.text.x=element_text(angle=90, size = 5), legend.text=element_text(size=5))

Comment on this article Share:

Brinda Murulidhara HW4

Read in a dataset

Descriptive statistics

Mean

Median

Standard Deviation

Frequencies

Median latitude and longitude grouped by township

Univariate visualisation

Explanation

Limitations

Bivariate Visualisation

Explanation

Limitations

Reuse

Citation