FluNet
Patrick Ford
2024-05-22
# Load necessary libraries
pacman::p_load(pacman, readr, dplyr, skimr, naniar, ggplot2, tidyr, patchwork)
# Load the dataset with appropriate encoding
my_data <- read_csv("VIW_FNT.csv", locale = locale(encoding = "UTF-8"))## Rows: 156291 Columns: 49
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (12): WHOREGION, FLUSEASON, HEMISPHERE, ITZ, COUNTRY_CODE, COUNTRY_AREA...
## dbl (35): ISO_YEAR, ISO_WEEK, MMWR_YEAR, MMWR_WEEK, SPEC_PROCESSED_NB, SPEC...
## date (2): ISO_WEEKSTARTDATE, MMWR_WEEKSTARTDATE
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.# Identify numeric and character columns
numeric_columns <- names(my_data)[sapply(my_data, is.numeric)]
character_columns <- names(my_data)[sapply(my_data, is.character)]
# Replace NA values in numeric columns with 0 (or another appropriate numeric value)
my_data <- my_data %>%
mutate(across(all_of(numeric_columns), ~ replace_na(.x, 0)))
# Replace NA values in character columns with empty string (or another appropriate character value)
my_data <- my_data %>%
mutate(across(all_of(character_columns), ~ replace_na(.x, "")))
# Basic Summary
summary(my_data)## WHOREGION FLUSEASON HEMISPHERE ITZ
## Length:156291 Length:156291 Length:156291 Length:156291
## Class :character Class :character Class :character Class :character
## Mode :character Mode :character Mode :character Mode :character
##
##
##
## COUNTRY_CODE COUNTRY_AREA_TERRITORY ISO_WEEKSTARTDATE ISO_YEAR
## Length:156291 Length:156291 Min. :1995-01-02 Min. :1995
## Class :character Class :character 1st Qu.:2012-02-06 1st Qu.:2012
## Mode :character Mode :character Median :2017-02-20 Median :2017
## Mean :2015-11-07 Mean :2015
## 3rd Qu.:2021-02-22 3rd Qu.:2021
## Max. :2024-05-13 Max. :2024
## ISO_WEEK MMWR_WEEKSTARTDATE MMWR_YEAR MMWR_WEEK
## Min. : 1.00 Min. :1995-01-01 Min. :1995 Min. : 1.00
## 1st Qu.:12.00 1st Qu.:2012-02-05 1st Qu.:2012 1st Qu.:12.00
## Median :25.00 Median :2017-02-19 Median :2017 Median :25.00
## Mean :25.78 Mean :2015-11-06 Mean :2015 Mean :25.78
## 3rd Qu.:40.00 3rd Qu.:2021-02-21 3rd Qu.:2021 3rd Qu.:40.00
## Max. :53.00 Max. :2024-05-12 Max. :2024 Max. :53.00
## ORIGIN_SOURCE SPEC_PROCESSED_NB SPEC_RECEIVED_NB AH1N12009
## Length:156291 Min. : 0.0 Min. : 0.0 Min. : 0.00
## Class :character 1st Qu.: 2.0 1st Qu.: 0.0 1st Qu.: 0.00
## Mode :character Median : 23.0 Median : 0.0 Median : 0.00
## Mean : 463.2 Mean : 295.9 Mean : 11.27
## 3rd Qu.: 91.0 3rd Qu.: 13.0 3rd Qu.: 1.00
## Max. :191785.0 Max. :191785.0 Max. :10575.00
## AH1 AH3 AH5 AH7N9
## Min. : 0.0000 Min. : 0 Min. : 0.000000 Min. :0.000000
## 1st Qu.: 0.0000 1st Qu.: 0 1st Qu.: 0.000000 1st Qu.:0.000000
## Median : 0.0000 Median : 0 Median : 0.000000 Median :0.000000
## Mean : 0.5522 Mean : 11 Mean : 0.002604 Mean :0.000282
## 3rd Qu.: 0.0000 3rd Qu.: 1 3rd Qu.: 0.000000 3rd Qu.:0.000000
## Max. :906.0000 Max. :14991 Max. :14.000000 Max. :6.000000
## ANOTSUBTYPED ANOTSUBTYPABLE AOTHER_SUBTYPE
## Min. : 0.00 Min. : 0.00000 Min. : 0.00000
## 1st Qu.: 0.00 1st Qu.: 0.00000 1st Qu.: 0.00000
## Median : 0.00 Median : 0.00000 Median : 0.00000
## Mean : 20.13 Mean : 0.01832 Mean : 0.00519
## 3rd Qu.: 0.00 3rd Qu.: 0.00000 3rd Qu.: 0.00000
## Max. :48835.00 Max. :58.00000 Max. :95.00000
## AOTHER_SUBTYPE_DETAILS INF_A BVIC_2DEL
## Length:156291 Min. : 0.00 Min. : 0.00000
## Class :character 1st Qu.: 0.00 1st Qu.: 0.00000
## Mode :character Median : 0.00 Median : 0.00000
## Mean : 42.99 Mean : 0.01976
## 3rd Qu.: 6.00 3rd Qu.: 0.00000
## Max. :48835.00 Max. :175.00000
## BVIC_3DEL BVIC_NODEL BVIC_DELUNK BYAM
## Min. :0.000000 Min. : 0.00 Min. : 0.00000 Min. : 0.0000
## 1st Qu.:0.000000 1st Qu.: 0.00 1st Qu.: 0.00000 1st Qu.: 0.0000
## Median :0.000000 Median : 0.00 Median : 0.00000 Median : 0.0000
## Mean :0.000409 Mean : 2.19 Mean : 0.06771 Mean : 0.9828
## 3rd Qu.:0.000000 3rd Qu.: 0.00 3rd Qu.: 0.00000 3rd Qu.: 0.0000
## Max. :5.000000 Max. :6596.00 Max. :129.00000 Max. :2641.0000
## BNOTDETERMINED INF_B INF_ALL INF_NEGATIVE
## Min. : -1.000 Min. : 0.00 Min. : 0.00 Min. : 0.0
## 1st Qu.: 0.000 1st Qu.: 0.00 1st Qu.: 0.00 1st Qu.: 0.0
## Median : 0.000 Median : 0.00 Median : 1.00 Median : 0.0
## Mean : 9.103 Mean : 12.28 Mean : 55.26 Mean : 193.3
## 3rd Qu.: 1.000 3rd Qu.: 2.00 3rd Qu.: 10.00 3rd Qu.: 0.0
## Max. :11264.000 Max. :11264.00 Max. :49007.00 Max. :147198.0
## ILI_ACTIVITY ADENO BOCA HUMAN_CORONA
## Min. :0.000 Min. : 0.0000 Min. : 0.00000 Min. : 0.0000
## 1st Qu.:0.000 1st Qu.: 0.0000 1st Qu.: 0.00000 1st Qu.: 0.0000
## Median :0.000 Median : 0.0000 Median : 0.00000 Median : 0.0000
## Mean :1.165 Mean : 0.8912 Mean : 0.06439 Mean : 0.4873
## 3rd Qu.:2.000 3rd Qu.: 0.0000 3rd Qu.: 0.00000 3rd Qu.: 0.0000
## Max. :6.000 Max. :376.0000 Max. :226.00000 Max. :708.0000
## METAPNEUMO PARAINFLUENZA RHINO RSV
## Min. : 0.0000 Min. : 0.000 Min. : 0.000 Min. : 0.000
## 1st Qu.: 0.0000 1st Qu.: 0.000 1st Qu.: 0.000 1st Qu.: 0.000
## Median : 0.0000 Median : 0.000 Median : 0.000 Median : 0.000
## Mean : 0.8256 Mean : 1.253 Mean : 1.944 Mean : 8.256
## 3rd Qu.: 0.0000 3rd Qu.: 0.000 3rd Qu.: 0.000 3rd Qu.: 0.000
## Max. :723.0000 Max. :609.000 Max. :1416.000 Max. :3523.000
## OTHERRESPVIRUS OTHER_RESPVIRUS_DETAILS LAB_RESULT_COMMENT
## Min. : 0.000 Length:156291 Length:156291
## 1st Qu.: 0.000 Class :character Class :character
## Median : 0.000 Mode :character Mode :character
## Mean : 1.036
## 3rd Qu.: 0.000
## Max. :732.000
## WCR_COMMENT ISO2 ISOYW MMWRYW
## Length:156291 Length:156291 Min. :199501 Min. :199501
## Class :character Class :character 1st Qu.:201206 1st Qu.:201206
## Mode :character Mode :character Median :201708 Median :201708
## Mean :201563 Mean :201563
## 3rd Qu.:202108 3rd Qu.:202108
## Max. :202420 Max. :202420# Extended Summary with 'skimr'
skim(my_data)| Name | my_data |
| Number of rows | 156291 |
| Number of columns | 49 |
| _______________________ | |
| Column type frequency: | |
| character | 12 |
| Date | 2 |
| numeric | 35 |
| ________________________ | |
| Group variables | None |
Variable type: character
| skim_variable | n_missing | complete_rate | min | max | empty | n_unique | whitespace |
|---|---|---|---|---|---|---|---|
| WHOREGION | 0 | 1 | 3 | 4 | 0 | 7 | 0 |
| FLUSEASON | 0 | 1 | 2 | 2 | 0 | 3 | 0 |
| HEMISPHERE | 0 | 1 | 2 | 2 | 0 | 2 | 0 |
| ITZ | 0 | 1 | 10 | 15 | 0 | 18 | 0 |
| COUNTRY_CODE | 0 | 1 | 3 | 3 | 0 | 186 | 0 |
| COUNTRY_AREA_TERRITORY | 0 | 1 | 4 | 70 | 0 | 186 | 0 |
| ORIGIN_SOURCE | 0 | 1 | 8 | 11 | 0 | 3 | 0 |
| AOTHER_SUBTYPE_DETAILS | 0 | 1 | 0 | 125 | 149312 | 82 | 0 |
| OTHER_RESPVIRUS_DETAILS | 0 | 1 | 0 | 320 | 132553 | 5593 | 0 |
| LAB_RESULT_COMMENT | 0 | 1 | 0 | 996 | 151688 | 1430 | 0 |
| WCR_COMMENT | 0 | 1 | 0 | 450 | 138621 | 11445 | 0 |
| ISO2 | 0 | 1 | 0 | 2 | 93 | 186 | 0 |
Variable type: Date
| skim_variable | n_missing | complete_rate | min | max | median | n_unique |
|---|---|---|---|---|---|---|
| ISO_WEEKSTARTDATE | 0 | 1 | 1995-01-02 | 2024-05-13 | 2017-02-20 | 1506 |
| MMWR_WEEKSTARTDATE | 0 | 1 | 1995-01-01 | 2024-05-12 | 2017-02-19 | 1506 |
Variable type: numeric
| skim_variable | n_missing | complete_rate | mean | sd | p0 | p25 | p50 | p75 | p100 | hist |
|---|---|---|---|---|---|---|---|---|---|---|
| ISO_YEAR | 0 | 1 | 2015.37 | 6.50 | 1995 | 2012 | 2017 | 2021 | 2024 | ▁▂▃▇▇ |
| ISO_WEEK | 0 | 1 | 25.78 | 15.70 | 1 | 12 | 25 | 40 | 53 | ▇▆▆▆▇ |
| MMWR_YEAR | 0 | 1 | 2015.37 | 6.50 | 1995 | 2012 | 2017 | 2021 | 2024 | ▁▂▃▇▇ |
| MMWR_WEEK | 0 | 1 | 25.78 | 15.70 | 1 | 12 | 25 | 40 | 53 | ▇▆▆▆▇ |
| SPEC_PROCESSED_NB | 0 | 1 | 463.20 | 3457.80 | 0 | 2 | 23 | 91 | 191785 | ▇▁▁▁▁ |
| SPEC_RECEIVED_NB | 0 | 1 | 295.94 | 3277.10 | 0 | 0 | 0 | 13 | 191785 | ▇▁▁▁▁ |
| AH1N12009 | 0 | 1 | 11.27 | 131.42 | 0 | 0 | 0 | 1 | 10575 | ▇▁▁▁▁ |
| AH1 | 0 | 1 | 0.55 | 10.48 | 0 | 0 | 0 | 0 | 906 | ▇▁▁▁▁ |
| AH3 | 0 | 1 | 11.00 | 124.37 | 0 | 0 | 0 | 1 | 14991 | ▇▁▁▁▁ |
| AH5 | 0 | 1 | 0.00 | 0.11 | 0 | 0 | 0 | 0 | 14 | ▇▁▁▁▁ |
| AH7N9 | 0 | 1 | 0.00 | 0.03 | 0 | 0 | 0 | 0 | 6 | ▇▁▁▁▁ |
| ANOTSUBTYPED | 0 | 1 | 20.13 | 378.66 | 0 | 0 | 0 | 0 | 48835 | ▇▁▁▁▁ |
| ANOTSUBTYPABLE | 0 | 1 | 0.02 | 0.61 | 0 | 0 | 0 | 0 | 58 | ▇▁▁▁▁ |
| AOTHER_SUBTYPE | 0 | 1 | 0.01 | 0.38 | 0 | 0 | 0 | 0 | 95 | ▇▁▁▁▁ |
| INF_A | 0 | 1 | 42.99 | 442.32 | 0 | 0 | 0 | 6 | 48835 | ▇▁▁▁▁ |
| BVIC_2DEL | 0 | 1 | 0.02 | 1.12 | 0 | 0 | 0 | 0 | 175 | ▇▁▁▁▁ |
| BVIC_3DEL | 0 | 1 | 0.00 | 0.03 | 0 | 0 | 0 | 0 | 5 | ▇▁▁▁▁ |
| BVIC_NODEL | 0 | 1 | 2.19 | 59.47 | 0 | 0 | 0 | 0 | 6596 | ▇▁▁▁▁ |
| BVIC_DELUNK | 0 | 1 | 0.07 | 1.54 | 0 | 0 | 0 | 0 | 129 | ▇▁▁▁▁ |
| BYAM | 0 | 1 | 0.98 | 22.53 | 0 | 0 | 0 | 0 | 2641 | ▇▁▁▁▁ |
| BNOTDETERMINED | 0 | 1 | 9.10 | 121.90 | -1 | 0 | 0 | 1 | 11264 | ▇▁▁▁▁ |
| INF_B | 0 | 1 | 12.28 | 140.00 | 0 | 0 | 0 | 2 | 11264 | ▇▁▁▁▁ |
| INF_ALL | 0 | 1 | 55.26 | 519.78 | 0 | 0 | 1 | 10 | 49007 | ▇▁▁▁▁ |
| INF_NEGATIVE | 0 | 1 | 193.26 | 2840.85 | 0 | 0 | 0 | 0 | 147198 | ▇▁▁▁▁ |
| ILI_ACTIVITY | 0 | 1 | 1.16 | 1.56 | 0 | 0 | 0 | 2 | 6 | ▇▁▂▁▁ |
| ADENO | 0 | 1 | 0.89 | 8.09 | 0 | 0 | 0 | 0 | 376 | ▇▁▁▁▁ |
| BOCA | 0 | 1 | 0.06 | 1.23 | 0 | 0 | 0 | 0 | 226 | ▇▁▁▁▁ |
| HUMAN_CORONA | 0 | 1 | 0.49 | 9.71 | 0 | 0 | 0 | 0 | 708 | ▇▁▁▁▁ |
| METAPNEUMO | 0 | 1 | 0.83 | 11.55 | 0 | 0 | 0 | 0 | 723 | ▇▁▁▁▁ |
| PARAINFLUENZA | 0 | 1 | 1.25 | 13.50 | 0 | 0 | 0 | 0 | 609 | ▇▁▁▁▁ |
| RHINO | 0 | 1 | 1.94 | 26.23 | 0 | 0 | 0 | 0 | 1416 | ▇▁▁▁▁ |
| RSV | 0 | 1 | 8.26 | 72.92 | 0 | 0 | 0 | 0 | 3523 | ▇▁▁▁▁ |
| OTHERRESPVIRUS | 0 | 1 | 1.04 | 17.50 | 0 | 0 | 0 | 0 | 732 | ▇▁▁▁▁ |
| ISOYW | 0 | 1 | 201563.16 | 649.42 | 199501 | 201206 | 201708 | 202108 | 202420 | ▁▂▃▆▇ |
| MMWRYW | 0 | 1 | 201563.02 | 649.52 | 199501 | 201206 | 201708 | 202108 | 202420 | ▁▂▃▆▇ |
# Missing Values Analysis
total_missing <- sum(is.na(my_data))
col_missing <- colSums(is.na(my_data))
# Print missing values summary
cat("Total missing values:", total_missing, "\n")## Total missing values: 0print(col_missing)## WHOREGION FLUSEASON HEMISPHERE
## 0 0 0
## ITZ COUNTRY_CODE COUNTRY_AREA_TERRITORY
## 0 0 0
## ISO_WEEKSTARTDATE ISO_YEAR ISO_WEEK
## 0 0 0
## MMWR_WEEKSTARTDATE MMWR_YEAR MMWR_WEEK
## 0 0 0
## ORIGIN_SOURCE SPEC_PROCESSED_NB SPEC_RECEIVED_NB
## 0 0 0
## AH1N12009 AH1 AH3
## 0 0 0
## AH5 AH7N9 ANOTSUBTYPED
## 0 0 0
## ANOTSUBTYPABLE AOTHER_SUBTYPE AOTHER_SUBTYPE_DETAILS
## 0 0 0
## INF_A BVIC_2DEL BVIC_3DEL
## 0 0 0
## BVIC_NODEL BVIC_DELUNK BYAM
## 0 0 0
## BNOTDETERMINED INF_B INF_ALL
## 0 0 0
## INF_NEGATIVE ILI_ACTIVITY ADENO
## 0 0 0
## BOCA HUMAN_CORONA METAPNEUMO
## 0 0 0
## PARAINFLUENZA RHINO RSV
## 0 0 0
## OTHERRESPVIRUS OTHER_RESPVIRUS_DETAILS LAB_RESULT_COMMENT
## 0 0 0
## WCR_COMMENT ISO2 ISOYW
## 0 0 0
## MMWRYW
## 0# Plot 1: Visualize missing values
p_miss <- gg_miss_var(my_data) +
labs(title = "Missing Values in Dataset",
x = "Variables",
y = "Number of Missing Values")
print(p_miss)
# Visualizations for Structure
str(my_data)## tibble [156,291 × 49] (S3: tbl_df/tbl/data.frame)
## $ WHOREGION : chr [1:156291] "EUR" "AMR" "EUR" "WPR" ...
## $ FLUSEASON : chr [1:156291] "NH" "YR" "NH" "YR" ...
## $ HEMISPHERE : chr [1:156291] "NH" "SH" "NH" "NH" ...
## $ ITZ : chr [1:156291] "FLU_WST_ASIA" "FLU_TRP_SAMR" "FLU_SW_EUR" "FLU_SE_ASIA" ...
## $ COUNTRY_CODE : chr [1:156291] "AZE" "BRA" "HRV" "PHL" ...
## $ COUNTRY_AREA_TERRITORY : chr [1:156291] "Azerbaijan" "Brazil" "Croatia" "Philippines" ...
## $ ISO_WEEKSTARTDATE : Date[1:156291], format: "2015-11-16" "2009-06-15" ...
## $ ISO_YEAR : num [1:156291] 2015 2009 2014 2004 2024 ...
## $ ISO_WEEK : num [1:156291] 47 25 7 3 7 33 21 46 2 43 ...
## $ MMWR_WEEKSTARTDATE : Date[1:156291], format: "2015-11-15" "2009-06-14" ...
## $ MMWR_YEAR : num [1:156291] 2015 2009 2014 2004 2024 ...
## $ MMWR_WEEK : num [1:156291] 46 25 7 2 7 33 20 46 2 43 ...
## $ ORIGIN_SOURCE : chr [1:156291] "NONSENTINEL" "NOTDEFINED" "SENTINEL" "NOTDEFINED" ...
## $ SPEC_PROCESSED_NB : num [1:156291] 5 227 149 58 169 ...
## $ SPEC_RECEIVED_NB : num [1:156291] 0 267 0 0 169 ...
## $ AH1N12009 : num [1:156291] 0 85 0 0 52 0 0 264 0 18 ...
## $ AH1 : num [1:156291] 0 0 0 0 0 0 0 0 0 0 ...
## $ AH3 : num [1:156291] 0 1 0 0 0 0 1 30 0 0 ...
## $ AH5 : num [1:156291] 0 0 0 0 0 0 0 0 0 0 ...
## $ AH7N9 : num [1:156291] 0 0 0 0 0 0 0 0 0 0 ...
## $ ANOTSUBTYPED : num [1:156291] 0 34 0 0 0 0 1 4 0 0 ...
## $ ANOTSUBTYPABLE : num [1:156291] 0 0 0 0 0 0 0 0 0 0 ...
## $ AOTHER_SUBTYPE : num [1:156291] 0 0 0 0 0 0 0 0 0 0 ...
## $ AOTHER_SUBTYPE_DETAILS : chr [1:156291] "" "" "" "" ...
## $ INF_A : num [1:156291] 0 120 0 0 52 0 2 298 0 18 ...
## $ BVIC_2DEL : num [1:156291] 0 0 0 0 0 0 0 0 0 0 ...
## $ BVIC_3DEL : num [1:156291] 0 0 0 0 0 0 0 0 0 0 ...
## $ BVIC_NODEL : num [1:156291] 0 0 0 0 13 0 0 3 0 0 ...
## $ BVIC_DELUNK : num [1:156291] 0 0 0 0 0 0 0 0 0 0 ...
## $ BYAM : num [1:156291] 0 0 0 0 0 0 4 7 0 0 ...
## $ BNOTDETERMINED : num [1:156291] 0 7 0 0 5 0 0 0 0 0 ...
## $ INF_B : num [1:156291] 0 7 0 0 18 0 4 10 0 0 ...
## $ INF_ALL : num [1:156291] 0 127 0 0 70 0 6 308 0 18 ...
## $ INF_NEGATIVE : num [1:156291] 0 0 0 0 99 ...
## $ ILI_ACTIVITY : num [1:156291] 0 6 0 2 0 0 0 3 0 3 ...
## $ ADENO : num [1:156291] 0 0 0 0 0 0 11 0 0 0 ...
## $ BOCA : num [1:156291] 0 0 0 0 0 0 0 0 0 0 ...
## $ HUMAN_CORONA : num [1:156291] 0 0 0 0 0 0 0 0 0 0 ...
## $ METAPNEUMO : num [1:156291] 0 0 0 0 0 0 1 0 0 0 ...
## $ PARAINFLUENZA : num [1:156291] 0 0 0 0 0 0 51 0 0 0 ...
## $ RHINO : num [1:156291] 0 0 0 0 0 0 0 0 0 0 ...
## $ RSV : num [1:156291] 0 0 0 0 1 0 30 0 11 0 ...
## $ OTHERRESPVIRUS : num [1:156291] 0 0 0 0 0 0 0 0 0 0 ...
## $ OTHER_RESPVIRUS_DETAILS: chr [1:156291] "" "0" "" "Rhinovirus" ...
## $ LAB_RESULT_COMMENT : chr [1:156291] "" "No unsubtyped or antiviral resistence was found." "" "" ...
## $ WCR_COMMENT : chr [1:156291] "" "The Flu seasonal activity is low and H1N1 pandemic first detection." "" "" ...
## $ ISO2 : chr [1:156291] "AZ" "BR" "HR" "PH" ...
## $ ISOYW : num [1:156291] 201547 200925 201407 200403 202407 ...
## $ MMWRYW : num [1:156291] 201546 200925 201407 200402 202407 ...# Convert appropriate columns to factors or dates
my_data <- my_data %>%
mutate(
FLUSEASON = as.factor(FLUSEASON),
HEMISPHERE = as.factor(HEMISPHERE),
ISO_WEEKSTARTDATE = as.Date(ISO_WEEKSTARTDATE, format="%Y-%m-%d"),
MMWR_WEEKSTARTDATE = as.Date(MMWR_WEEKSTARTDATE, format="%Y-%m-%d")
)
# Recheck the structure
str(my_data)## tibble [156,291 × 49] (S3: tbl_df/tbl/data.frame)
## $ WHOREGION : chr [1:156291] "EUR" "AMR" "EUR" "WPR" ...
## $ FLUSEASON : Factor w/ 3 levels "NH","SH","YR": 1 3 1 3 3 1 2 3 1 1 ...
## $ HEMISPHERE : Factor w/ 2 levels "NH","SH": 1 2 1 1 1 1 2 1 1 1 ...
## $ ITZ : chr [1:156291] "FLU_WST_ASIA" "FLU_TRP_SAMR" "FLU_SW_EUR" "FLU_SE_ASIA" ...
## $ COUNTRY_CODE : chr [1:156291] "AZE" "BRA" "HRV" "PHL" ...
## $ COUNTRY_AREA_TERRITORY : chr [1:156291] "Azerbaijan" "Brazil" "Croatia" "Philippines" ...
## $ ISO_WEEKSTARTDATE : Date[1:156291], format: "2015-11-16" "2009-06-15" ...
## $ ISO_YEAR : num [1:156291] 2015 2009 2014 2004 2024 ...
## $ ISO_WEEK : num [1:156291] 47 25 7 3 7 33 21 46 2 43 ...
## $ MMWR_WEEKSTARTDATE : Date[1:156291], format: "2015-11-15" "2009-06-14" ...
## $ MMWR_YEAR : num [1:156291] 2015 2009 2014 2004 2024 ...
## $ MMWR_WEEK : num [1:156291] 46 25 7 2 7 33 20 46 2 43 ...
## $ ORIGIN_SOURCE : chr [1:156291] "NONSENTINEL" "NOTDEFINED" "SENTINEL" "NOTDEFINED" ...
## $ SPEC_PROCESSED_NB : num [1:156291] 5 227 149 58 169 ...
## $ SPEC_RECEIVED_NB : num [1:156291] 0 267 0 0 169 ...
## $ AH1N12009 : num [1:156291] 0 85 0 0 52 0 0 264 0 18 ...
## $ AH1 : num [1:156291] 0 0 0 0 0 0 0 0 0 0 ...
## $ AH3 : num [1:156291] 0 1 0 0 0 0 1 30 0 0 ...
## $ AH5 : num [1:156291] 0 0 0 0 0 0 0 0 0 0 ...
## $ AH7N9 : num [1:156291] 0 0 0 0 0 0 0 0 0 0 ...
## $ ANOTSUBTYPED : num [1:156291] 0 34 0 0 0 0 1 4 0 0 ...
## $ ANOTSUBTYPABLE : num [1:156291] 0 0 0 0 0 0 0 0 0 0 ...
## $ AOTHER_SUBTYPE : num [1:156291] 0 0 0 0 0 0 0 0 0 0 ...
## $ AOTHER_SUBTYPE_DETAILS : chr [1:156291] "" "" "" "" ...
## $ INF_A : num [1:156291] 0 120 0 0 52 0 2 298 0 18 ...
## $ BVIC_2DEL : num [1:156291] 0 0 0 0 0 0 0 0 0 0 ...
## $ BVIC_3DEL : num [1:156291] 0 0 0 0 0 0 0 0 0 0 ...
## $ BVIC_NODEL : num [1:156291] 0 0 0 0 13 0 0 3 0 0 ...
## $ BVIC_DELUNK : num [1:156291] 0 0 0 0 0 0 0 0 0 0 ...
## $ BYAM : num [1:156291] 0 0 0 0 0 0 4 7 0 0 ...
## $ BNOTDETERMINED : num [1:156291] 0 7 0 0 5 0 0 0 0 0 ...
## $ INF_B : num [1:156291] 0 7 0 0 18 0 4 10 0 0 ...
## $ INF_ALL : num [1:156291] 0 127 0 0 70 0 6 308 0 18 ...
## $ INF_NEGATIVE : num [1:156291] 0 0 0 0 99 ...
## $ ILI_ACTIVITY : num [1:156291] 0 6 0 2 0 0 0 3 0 3 ...
## $ ADENO : num [1:156291] 0 0 0 0 0 0 11 0 0 0 ...
## $ BOCA : num [1:156291] 0 0 0 0 0 0 0 0 0 0 ...
## $ HUMAN_CORONA : num [1:156291] 0 0 0 0 0 0 0 0 0 0 ...
## $ METAPNEUMO : num [1:156291] 0 0 0 0 0 0 1 0 0 0 ...
## $ PARAINFLUENZA : num [1:156291] 0 0 0 0 0 0 51 0 0 0 ...
## $ RHINO : num [1:156291] 0 0 0 0 0 0 0 0 0 0 ...
## $ RSV : num [1:156291] 0 0 0 0 1 0 30 0 11 0 ...
## $ OTHERRESPVIRUS : num [1:156291] 0 0 0 0 0 0 0 0 0 0 ...
## $ OTHER_RESPVIRUS_DETAILS: chr [1:156291] "" "0" "" "Rhinovirus" ...
## $ LAB_RESULT_COMMENT : chr [1:156291] "" "No unsubtyped or antiviral resistence was found." "" "" ...
## $ WCR_COMMENT : chr [1:156291] "" "The Flu seasonal activity is low and H1N1 pandemic first detection." "" "" ...
## $ ISO2 : chr [1:156291] "AZ" "BR" "HR" "PH" ...
## $ ISOYW : num [1:156291] 201547 200925 201407 200403 202407 ...
## $ MMWRYW : num [1:156291] 201546 200925 201407 200402 202407 ...# Visualizing key numeric columns
numeric_long <- my_data %>%
select(all_of(numeric_columns)) %>%
gather(key = "Variable", value = "Value")
# Plot 2: Histograms for Numeric Columns
p_hist <- ggplot(numeric_long, aes(x = Value)) +
geom_histogram(bins = 30, fill = "blue", alpha = 0.7) +
facet_wrap(~Variable, scales = "free") +
theme_minimal() +
labs(title = "Histograms of Numeric Columns",
x = "Value",
y = "Frequency")
print(p_hist)
# Plot 3: Boxplot for a numeric column by FLUSEASON
p_box <- ggplot(my_data, aes(x = FLUSEASON, y = SPEC_PROCESSED_NB)) +
geom_boxplot() +
theme_minimal() +
labs(title = "Boxplot of SPEC_PROCESSED_NB by FLUSEASON",
x = "FLUSEASON",
y = "SPEC_PROCESSED_NB")
print(p_box)
# Plot 4: Time Series Plot for SPEC_PROCESSED_NB over ISO_WEEKSTARTDATE
p_time <- ggplot(my_data, aes(x = ISO_WEEKSTARTDATE, y = SPEC_PROCESSED_NB)) +
geom_line() +
theme_minimal() +
labs(title = "Time Series of SPEC_PROCESSED_NB",
x = "ISO Week Start Date",
y = "SPEC_PROCESSED_NB")
print(p_time)