Final Project: NYC 311 Service

NYC311’s mission is to provide the public with quick, easy access to all New York City government services and information while offering the best customer service. We help Agencies improve service delivery by allowing them to focus on their core missions and manage their workload efficiently. We also provide insight to improve City government through accurate, consistent measurement and analysis of service delivery. NYC311 is available 24 hours a day, 7 days a week, 365 days a year. We work to make government services accessible for all

Project Goal

NYC311 Service Requests & Resolution Analysis - Text Mining

Data Sources

NYC Open Data API - https://dev.socrata.com/foundry/data.cityofnewyork.us/fhrw-4uyv

NYC311 Twitter: https://twitter.com/nyc311 - NYC311 is your source for New York City non-emergency government services. Account monitored 24/7. User policy: http://on.nyc.gov/1evyJgB

Data Science Workflow

library(plyr) #loading plyr first then dplyr as there are conflicts in execution if done otherwise
library(tidyverse)
library(knitr)

Data Acquisition

NYC OpenData API

Getting SR History using the JSON API and load it into a data frame - 150,000 SRs
library(jsonlite)  

api_tkn <- "$$app_token=ZHxqxXyUSoZlBvzxpZsTT9QjG"
api_endpoint <- "https://data.cityofnewyork.us/resource/fhrw-4uyv.json?"
api_limit <- "&$limit=150000"
#api_filter <- "&borough=BRONX"
request_json <- fromJSON(paste0(api_endpoint, api_tkn, api_limit))
class(request_json)
## [1] "data.frame"
colnames(request_json)
##  [1] "address_type"                   "agency"                        
##  [3] "agency_name"                    "bbl"                           
##  [5] "borough"                        "city"                          
##  [7] "closed_date"                    "community_board"               
##  [9] "complaint_type"                 "created_date"                  
## [11] "cross_street_1"                 "cross_street_2"                
## [13] "descriptor"                     "facility_type"                 
## [15] "incident_address"               "incident_zip"                  
## [17] "latitude"                       "location"                      
## [19] "location_type"                  "longitude"                     
## [21] "open_data_channel_type"         "park_borough"                  
## [23] "park_facility_name"             "resolution_action_updated_date"
## [25] "resolution_description"         "status"                        
## [27] "street_name"                    "unique_key"                    
## [29] "x_coordinate_state_plane"       "y_coordinate_state_plane"      
## [31] "due_date"                       "intersection_street_1"         
## [33] "intersection_street_2"          "taxi_pick_up_location"         
## [35] "bridge_highway_direction"       "bridge_highway_name"           
## [37] "bridge_highway_segment"         "road_ramp"                     
## [39] "taxi_company_borough"           "landmark"                      
## [41] "vehicle_type"
nrow(request_json)
## [1] 150000
head(request_json,1)
##   address_type agency                                        agency_name
## 1      ADDRESS    HPD Department of Housing Preservation and Development
##          bbl  borough     city             closed_date community_board
## 1 3050560064 BROOKLYN BROOKLYN 2011-11-25T00:00:00.000     09 BROOKLYN
##   complaint_type            created_date cross_street_1 cross_street_2
## 1       NONCONST 2011-11-21T00:00:00.000 BEDFORD AVENUE  ROGERS AVENUE
##   descriptor facility_type    incident_address incident_zip
## 1     VERMIN           N/A 181 CLARKSON AVENUE        11226
##            latitude location.type location.coordinates
## 1 40.65519246467765         Point  -73.95402, 40.65519
##          location_type          longitude open_data_channel_type
## 1 RESIDENTIAL BUILDING -73.95402339048265                UNKNOWN
##   park_borough park_facility_name resolution_action_updated_date
## 1     BROOKLYN        Unspecified        2011-11-25T00:00:00.000
##                                                                                                                                                                      resolution_description
## 1 The Department of Housing Preservation and Development inspected the following conditions. Violations were issued. Information about specific violations is available at www.nyc.gov/hpd.
##   status     street_name unique_key x_coordinate_state_plane
## 1 Closed CLARKSON AVENUE   21931039                   997007
##   y_coordinate_state_plane due_date intersection_street_1
## 1                   177984     <NA>                  <NA>
##   intersection_street_2 taxi_pick_up_location bridge_highway_direction
## 1                  <NA>                  <NA>                     <NA>
##   bridge_highway_name bridge_highway_segment road_ramp
## 1                <NA>                   <NA>      <NA>
##   taxi_company_borough landmark vehicle_type
## 1                 <NA>     <NA>         <NA>

Data Exploration

Most common complaint types (top 50)

#library(tidyverse)

dataset <- request_json
ggplot(subset(dataset, complaint_type %in% count(dataset, complaint_type, sort=T)[1:50,]$complaint_type), aes(complaint_type)) + 
  geom_histogram(stat = "count") +
  labs(x="Complaint Type", y="Service Requests") +
  coord_flip() + theme_bw()
## Warning: Ignoring unknown parameters: binwidth, bins, pad

Most common complaint types by borough and status

dataset_qckfilt <- subset(dataset, complaint_type %in% count(dataset, complaint_type, sort=T)[1:50,]$complaint_type)
nrow(dataset_qckfilt)
## [1] 142079
dataset_qckfilt <- dataset_qckfilt %>% select(complaint_type, borough, status) 
ggplot(dataset_qckfilt, aes(x=status, y = complaint_type )) +
  geom_point() +
  geom_count() + 
  facet_wrap(~borough)

Service Request Resolutions Tidying and Analysis - Using Tidytext

Most frequent words used in NYC311 Service Requests

library(tidytext)

data(stop_words)
tokenized_resolutions <- dataset %>%
  select(complaint_type, descriptor, street_name, city, due_date, resolution_description, borough, open_data_channel_type) %>%
  filter(!str_detect(borough, "Unspecified")) %>% 
  unnest_tokens(word, resolution_description) %>%
  anti_join(stop_words) %>%
  group_by(borough, word) %>%
  tally()

tokenized_resolutions %>% glimpse()
## Observations: 3,227
## Variables: 3
## $ borough <chr> "BRONX", "BRONX", "BRONX", "BRONX", "BRONX", "BRONX", ...
## $ word    <chr> "1", "10", "120", "14", "152", "19", "21", "212", "287...
## $ n       <int> 16, 33, 28, 72, 24, 24, 56, 853, 9, 24, 8, 367, 1770, ...
tokenized_resolutions %>%
  group_by(borough) %>%
  top_n(25) %>%
  arrange(desc(n)) %>%
  ggplot(aes(x = reorder(word, n), y = n, fill = factor(borough))) +
  geom_bar(stat = "identity") +
  theme(legend.position = "none") +
  facet_wrap(~borough, scales = "free") + 
  coord_flip() +
  labs(x = "Words",
       y = "Frequency",
       title = "Top words used in NYC311 Service Requests by Borough",
       subtitle = "")

Determining terms/words truly characteristic for SRs by Borough leveraging textmining (TF-IDF)

tf_idf_words <- tokenized_resolutions %>%
  bind_tf_idf(word, borough, n) %>%
  arrange(desc(tf_idf))
tf_idf_words
## # A tibble: 3,227 x 6
## # Groups:   borough [5]
##    borough       word          n       tf   idf   tf_idf
##    <chr>         <chr>     <int>    <dbl> <dbl>    <dbl>
##  1 STATEN ISLAND pruning      42 0.000640 0.511 0.000327
##  2 MANHATTAN     attend      420 0.000966 0.223 0.000216
##  3 QUEENS        spring       42 0.000119 1.61  0.000191
##  4 STATEN ISLAND trees        22 0.000335 0.511 0.000171
##  5 STATEN ISLAND cycle        21 0.000320 0.511 0.000163
##  6 STATEN ISLAND prunes       21 0.000320 0.511 0.000163
##  7 STATEN ISLAND reviews      21 0.000320 0.511 0.000163
##  8 BRONX         fi          269 0.000585 0.223 0.000131
##  9 STATEN ISLAND intensity     9 0.000137 0.916 0.000126
## 10 STATEN ISLAND rain          9 0.000137 0.916 0.000126
## # ... with 3,217 more rows

Cleaning up the tf_idf data set from irrelevant or obvious words affecting the analysis

tf_idf_words_cln <- tf_idf_words %>% filter(!str_detect(word, "[[:digit:]]+")) %>% 
                filter(!str_detect(word, "[[:punct:]]+")) %>%
                filter(!str_detect(word, "bronx|brooklyn|manhattan|queens|staten island"))

Presenting characterisitc terms/words for SRs by Borough

tf_idf_words_cln %>% 
  top_n(25) %>%
  arrange(desc(tf_idf)) %>%
  ggplot(aes(x = reorder(word, tf_idf), y = tf_idf, fill = borough)) +
  geom_col() +
  labs(x = "Words", y = "tf-idf",
       title = "Distinctive words used in NYC311 Service Requests by Borough",
       subtitle = "") +
  coord_flip() +
  theme(legend.position = "none") +
  facet_wrap(~ borough, scales = "free")
## Selecting by tf_idf

Map Analysis

Preparing and tidying up the data for map plotting

dataset_map <- subset(dataset, complaint_type %in% count(dataset, complaint_type, sort=T)[1:50,]$complaint_type)
dataset_map <- dataset_map %>% select(complaint_type, borough, latitude, longitude) %>% drop_na()

#library(plyr)
counts <- ddply(dataset_map, .(complaint_type), "count")
counts_filtered <- filter(counts, freq > 80)
counts_filtered$freq <- as.numeric(counts_filtered$freq)
counts_filtered$longitude <- as.numeric(counts_filtered$longitude)
counts_filtered$latitude <- as.numeric(counts_filtered$latitude)

Map Plotting

#install.packages("rworldmap")
#install.packages("rworldxtra")

library(rworldmap)
library(rworldxtra)

newmap <- getMap(resolution = "high")
#nyc_coorflimits <- data.frame( long = c(-74.5, -73.5), lat = c(40.5, 41), stringsAsFactors = FALSE)

nyc <- ggplot() + geom_polygon(data = newmap, aes(x=long, y = lat, group = group), fill = "gray", color = "blue")  + xlim(-74.5, -73.5) + ylim(40.5, 41)

nyc_SRs <- nyc + 
  geom_point(data=counts_filtered, aes(longitude, latitude, size=freq), colour="red")  + 
#  facet_wrap(~complaint_type, scales = "free") + (Working on the console, not working on RMarkdown)
  labs(x = "Longitude", y = "Latitude", title = "Highest Number of SRs by Complaint Type") + scale_size(name="# of SRs")
nyc_SRs

Map with facets not working in RMarkdown. Image of the Map Plot as it appears in the RStudio Console
library("png")
pp <- readPNG("MapSRsbyComplType.png")
plot.new() 
rasterImage(pp,0,0,1,1)

Service Request Resolutions Tidying and Analysis - Using TM

library(tm)
library(wordcloud)

Filtering dataset to the most relevant Complaint Types

dataset_filt <- subset(dataset, complaint_type %in% count(dataset, complaint_type, sort=T)[1:50,]$complaint_type)
sr_resolution <- dataset_filt$resolution_description

Cleaning up non-standard characters (encoding conversion)

sr_resolution_cln <- sr_resolution %>% iconv("latin1", "ASCII")
control <- list(stopwords=TRUE, removePunctuation=TRUE, removeNumbers=TRUE, minDocFreq=5) # stemming=TRUE does not provide much value

Creating Corpus and TDM

sr_corpus <- VCorpus(VectorSource(sr_resolution_cln))
sr_tdm <- TermDocumentMatrix(sr_corpus, control)
sr_tdm
## <<TermDocumentMatrix (terms: 786, documents: 142079)>>
## Non-/sparse entries: 1820508/109853586
## Sparsity           : 98%
## Maximal term length: 21
## Weighting          : term frequency (tf)

Removing sparse terms (80% of sparse percentage of empty)

sr_tdm_unsprsd <- removeSparseTerms(sr_tdm, 0.8)
sr_tdm_unsprsd
## <<TermDocumentMatrix (terms: 18, documents: 142079)>>
## Non-/sparse entries: 961420/1596002
## Sparsity           : 62%
## Maximal term length: 12
## Weighting          : term frequency (tf)

Top terms by frequency (mentioned at least 50 times)

length(findFreqTerms(sr_tdm_unsprsd,50))
## [1] 18
sr_topterms <- findFreqTerms(sr_tdm_unsprsd,50)
sr_topterms
##  [1] "closed"       "complaint"    "condition"    "conditions"  
##  [5] "department"   "development"  "exists"       "file"        
##  [9] "following"    "housing"      "information"  "inspected"   
## [13] "issued"       "new"          "please"       "preservation"
## [17] "still"        "violations"

Find top associations for the top terms (lower correlation limit of 0.4). More consistent term association patterns found in service requests

sr_topterms <- sr_topterms[!is.na(sr_topterms)]
sr_assocs <- findAssocs(sr_tdm_unsprsd, sr_topterms[1:5], 0.4) 
lapply(sr_assocs, function(x) kable(x))
## $closed
## 
## 
##                    x
## -------------  -----
## development     0.74
## housing         0.74
## preservation    0.74
## following       0.70
## still           0.57
## exists          0.53
## file            0.43
## 
## $complaint
## 
## 
##                    x
## -------------  -----
## still           0.72
## exists          0.64
## please          0.53
## file            0.48
## development     0.43
## housing         0.43
## preservation    0.43
## 
## $condition
## 
## 
##              x
## -------  -----
## still     0.71
## exists    0.68
## file      0.54
## please    0.42
## 
## $conditions
## 
## 
##                    x
## -------------  -----
## following       0.96
## development     0.82
## housing         0.82
## preservation    0.82
## violations      0.57
## issued          0.52
## inspected       0.43
## 
## $department
## 
## 
## |  x|
## |--:|

Creating a WordCloud for the top terms/words in the SRs

library(wordcloud)
sr_tdm_cloud <- as.matrix(sr_tdm_unsprsd)
v <- sort(rowSums(sr_tdm_cloud),decreasing=TRUE)
d <- data.frame(word=names(v),freq=v)   
wordcloud(d$word,d$freq,max.words=50, min.freq=10, colors=brewer.pal(8, 'Dark2'))

NYC311 Tweets Analysis

Data Collection and Exploration

devtools::install_github(“mkearney/rtweet”) # Latest working version of rtweet, this is preferred version to use

API Set-up (Application Name and security context). Commands commented and keys masked

library(rtweet)

##appname <- "nyc311sentiment_analysis"
## key <- "12345678901234567890"
##secret <- "12345678901234567890abcdefghijk"
# create token named "twitter_token"
##twitter_token <- rtweet::create_token(app = appname,
##                                      consumer_key = key,
##                                      consumer_secret = secret)

##home_directory <- "C:/DATA/HHP/Personal/Degrees/Ms. Data Science (CUNY)/R Working Dir"
##file_name <- file.path(home_directory,
##                       "twitter_token.rds")
## save token to home directory
##saveRDS(twitter_token, file = file_name)

## create and save environment variable
##cat(paste0("TWITTER_PAT=", file_name),
##    file = file.path(home_directory, ".Renviron"),
##    append = TRUE)

Search and collect 1000 tweets doing any mention to the “nyc311” service (hashtag, user, follower, etc.)

nyc311_tweets <- search_tweets("nyc311", n = 1100, include_rts = FALSE)

head(nyc311_tweets$text,5) %>% kable()
x
@KezNat @NYPD94Pct @NYCMayorsOffice I understand your concern. You may file an Illegal Parking Complaint here: https://t.co/xHlOQoqZwu or kindly DM me and I will gladly file it on your behalf.
@alf300 @NYC_DOT @nycgov @NYCMayor @NYCMayorsOffice @DanRosenthalNYC @RoryLancman Sorry for the disturbance. You may file an After-Hours Construction Noise Complaint here: https://t.co/2KULvb99GG or kindly DM me to file it on your behalf.
.@NYCDHS Codigo azul esta en efecto hasta mañana, viernes, 7 de diciembre a las 8:00 AM. Si vez a algien sin hogar durante esta temperatura baja, por favor llámanos al 311 https://t.co/kYFdEOazeH
@PastorKebreau Thank you for bringing this to our attention. Kindly DM me and I will gladly assist you further.
@GabrielleDeP20 I understand your concern. For privately owned buildings, you may file a Smoking Complaint here: https://t.co/Pb21Is93Og or DM me to file it for you. For NYCHA building, you must reach out to NYCHA Customer Contact Center at 718-707-7771 https://t.co/3AllJpYxhR.

Sample of Users tweeting about “nyc311”

nyc311_users <- users_data(nyc311_tweets) %>% unique()
kable(head(head(nyc311_users[,c(3,4,8,9)])))
name location followers_count friends_count
New York City 311 New York City 323035 234
OLC-11249 New York City 84 308
Pastor Adlerette Kebreau usa 248 746
Gabrielle DePalo Manhattan, NY 21 26
Chevi Friedman 74 166
SamBen 5 24

Plot “nyc311” Tweets Time series (Last 7-9 days)

ts_plot(nyc311_tweets, "24 hours", col=c("blue")) + theme_minimal() + theme(plot.title = ggplot2::element_text(face = "bold")) + labs(x = "Date", y = "# of Tweets", title = "NYC311 Tweets in the last 7 days")

Sentiment Analysis - Syuzhet Package

‘Syuzhet’ breaks the text/words into 10 different emotions - anger, anticipation, disgust, fear, joy, sadness, surprise, trust, negative and positive.

Determine “nyc311” Tweet’s Emotions

#devtools::install_github("mjockers/syuzhet")
library(syuzhet)

nyc311_tweets_txt <- as.vector(nyc311_tweets$text)
emotion_df <- get_nrc_sentiment(nyc311_tweets_txt)
twt_emotion_df <- cbind(nyc311_tweets_txt, emotion_df) 
kable(head(twt_emotion_df,3))
nyc311_tweets_txt anger anticipation disgust fear joy sadness surprise trust negative positive
@KezNat @NYPD94Pct @NYCMayorsOffice I understand your concern. You may file an Illegal Parking Complaint here: https://t.co/xHlOQoqZwu or kindly DM me and I will gladly file it on your behalf. 2 0 1 1 0 1 0 0 2 0
@alf300 @NYC_DOT @nycgov @NYCMayor @NYCMayorsOffice @DanRosenthalNYC @RoryLancman Sorry for the disturbance. You may file an After-Hours Construction Noise Complaint here: https://t.co/2KULvb99GG or kindly DM me to file it on your behalf. 2 0 0 1 0 1 1 0 3 0
.@NYCDHS Codigo azul esta en efecto hasta mañana, viernes, 7 de diciembre a las 8:00 AM. Si vez a algien sin hogar durante esta temperatura baja, por favor llámanos al 311 https://t.co/kYFdEOazeH 1 0 1 1 0 1 0 0 1 0

Sentiment Scoring

sent.value <- get_sentiment(nyc311_tweets_txt)

Positive Tweets

positive.tweets <- nyc311_tweets_txt[sent.value > 0]
kable(head(positive.tweets,5))
x
@PastorKebreau Thank you for bringing this to our attention. Kindly DM me and I will gladly assist you further.
@jpicaro74 @NYPD121Pct Good morning and thanks for the pictures. If this is dangerous, call 911. If this is not dangerous, you can report an abandoned vehicle without license plates here: https://t.co/wJuf3Ldc5Y or DM me if you need assistance with filing. https://t.co/hDTCu9JZPB
@NYC_DOT Thank you for looping us in. Hi, @Mason_Transport you may report illegal parking in progress here: https://t.co/Xyto97vssS or you can DM me for assistance with filing. https://t.co/hDTCu9JZPB
@NYC_DOT Thank you for looping us in. Hi, @arnie09527558 @NYCMayor @BilldeBlasio @nycgov @NYCMayorsOffice @NotifyNYC @NYCHousing you can report visible dense smoke in the air from a rooftop chimney here: https://t.co/dZXcJB864h or DM me & I’ll file. https://t.co/hDTCu9JZPB
@GNAnegativeaxis @NYCHRA @NYGovCuomo @NYCMayor Good evening, if you feel you have been wronged. You may file an Agency Feedback complaint to the Commissioner for Human Resources Administration here: https://t.co/SNA3Y7aapp or DM me for assistance filing.

Most Positive Tweet

most.positive <- nyc311_tweets_txt[sent.value == max(sent.value)]
most.positive
## [1] "Find the perfect holiday event with the #311Weekend! \n\nTake a photo with Santa Claus at @NYCParks’ Holiday Blvd Park, light a tree &amp; drink cocoa at Holiday on the Hudson, and listen to your favorite tuba (yes tuba!) Christmas classics at @rockcenternyc right under the big tree. https://t.co/Gh594LZKpL"

Negative Tweets

negative.tweets <- nyc311_tweets_txt[sent.value < 0]
kable(head(negative.tweets,5))
x
@KezNat @NYPD94Pct @NYCMayorsOffice I understand your concern. You may file an Illegal Parking Complaint here: https://t.co/xHlOQoqZwu or kindly DM me and I will gladly file it on your behalf.
@alf300 @NYC_DOT @nycgov @NYCMayor @NYCMayorsOffice @DanRosenthalNYC @RoryLancman Sorry for the disturbance. You may file an After-Hours Construction Noise Complaint here: https://t.co/2KULvb99GG or kindly DM me to file it on your behalf.
.@NYCDHS Codigo azul esta en efecto hasta mañana, viernes, 7 de diciembre a las 8:00 AM. Si vez a algien sin hogar durante esta temperatura baja, por favor llámanos al 311 https://t.co/kYFdEOazeH
@GabrielleDeP20 I understand your concern. For privately owned buildings, you may file a Smoking Complaint here: https://t.co/Pb21Is93Og or DM me to file it for you. For NYCHA building, you must reach out to NYCHA Customer Contact Center at 718-707-7771 https://t.co/3AllJpYxhR.
.@NYCDHS’s Code Blue is in effect until tomorrow, Thursday, December 6 at 8:00 AM. If you see a homeless person outside in these frigid temperatures, please call us at 311. https://t.co/WYFH5ahuA6

Most Negative Tweet

most.negative <- nyc311_tweets_txt[sent.value <= min(sent.value)] 
most.negative 
## [1] "@nyc311 I’m bringing it to your attention before someone is god forbid robbed, killed or raped inside this section of this abandoned home! This act before something unfortunately bad occurs!"

Neutral Tweets

neutral.tweets <- nyc311_tweets_txt[sent.value == 0]
kable(head(neutral.tweets,5))
x
Ayuda a @NYCSanitation este invierno a mantener NYC limpio. Regístrese para ser un trabajador de la nieve y reciba un salario de $15 por hora. Vea los requerimientos y como aplicar en línea aquí: https://t.co/LzfHQ3FRxc https://t.co/PvprczRXYM
¿Listo para poner el árbol navideño? @FDNY quiere acordarle que su seguridad es primordial durante esta época Navideña. Cables y enchufes eléctricos son la causa de más de mitad de todos los incendios de árboles navideños. Aprenda como mantenerse seguro: https://t.co/INlY3rJuMk https://t.co/e4p0sppy8A
@NYC_DG Thank you for bringing this to our attention. You can file a Poster and Sign Complaint here https://t.co/HL3PFECiAi or DM me and I will file it on your behalf.
@deuchyle Thank you for bringing this to our attention. You can file a Noise from a Business Complaint here https://t.co/vQgxrkoZC7 or you can DM me and I will file it on your behalf.
Obtenga cobertura médica NYC a través de @NYStateofHealth. El periodo de inscripción está abierto ahora. Inscríbase antes del 15 de diciembre para obtener cobertura que comienza el 1 de enero de 2019. Aprenda más información aquí: https://t.co/QCNbI3BhrP https://t.co/7NfOHz4BNC

Total Tweets by Sentiment (Using plotly package)

#install.packages("plotly")
library(plotly)
category_sent <- ifelse(sent.value < 0, "Negative", ifelse(sent.value > 0, "Positive", "Neutral"))
totals <- data.frame(table(category_sent))
plot_ly(totals, labels = ~category_sent, values = ~Freq, type = 'pie',  textinfo = 'label+percent') %>% layout(title = 'NYC311 Tweets by Sentiment')

Conclusion

In terms of Sentiment Analysis for the “nyc311” tweets, the majority of them describe a positive or neutral sentiment (~67%), surprisingly not a considerable number of complaints or negative mentions being raised leveraging the Twitter channel and also, the NYC311 service uses it to provide resolution advice, status and redirection guidance to its users/followers.

Issues faced during the creation of this Analytics project

1) API Data Ingestion Limits - The NYC Open Data API started limiting the number of records I was able to retrieve. Initially, I was able to collect 500,000 records with no issues then while running my final report in R MArkdown, I started getting execution exceptions/errors that forced me to reduce the dataset to 150,000 records.
2) Map plotting in RMarkdown - My code to plot maps of the NYC area with SR statistics overlayed into multiple facets by complaint type worked perfectly in the RStudio Console. Once I tried the code within R Markdown it threw an exception/error not supporting facets and not overlaying SR statistics. I added a picture of the correct plot right after the affected code section as a reference. I would welcome advice on how to solve this.