Clean lints with lintr

Author: bostdm

chapters/05-01-hcup-amadeus-usecase.Rmd

@@ -255,8 +255,8 @@ saveRDS(avg_smoke_density, "smoke_density_avg_byZip.R")
 # # A tibble: 6 × 4
 #   ZCTA5CE10 avg_light avg_medium avg_heavy
 #   <fct>         <dbl>      <dbl>     <dbl>
-# 1 97833         0.129     0.194     0.419 
-# 2 97840         0.161     0.226     0.387 
+# 1 97833         0.129     0.194     0.419
+# 2 97840         0.161     0.226     0.387
 # 3 97330         0.290     0.129     0.0323
 # 4 97004         0.258     0.0968    0.0323
 # 5 97023         0.194     0.0968    0.0323
@@ -299,27 +299,27 @@ subset_data <- or_sedd_2021 %>%
   select(FEMALE, ZIP, PSTCO, AGE, RACE, AMONTH, starts_with("I10_"))
 head(subset_data)
 
-# [1] "FEMALE"               "ZIP"                  "PSTCO"               
-#  [4] "AGE"                  "RACE"                 "AMONTH"              
+# [1] "FEMALE"               "ZIP"                  "PSTCO"
+#  [4] "AGE"                  "RACE"                 "AMONTH"
 #  [7] "I10_DX_Visit_Reason1" "I10_DX_Visit_Reason2" "I10_DX_Visit_Reason3"
-# [10] "I10_DX1"              "I10_DX2"              "I10_DX3"             
-# [13] "I10_DX4"              "I10_DX5"              "I10_DX6"             
-# [16] "I10_DX7"              "I10_DX8"              "I10_DX9"             
-# [19] "I10_DX10"             "I10_DX11"             "I10_DX12"            
-# [22] "I10_DX13"             "I10_DX14"             "I10_DX15"            
-# [25] "I10_DX16"             "I10_DX17"             "I10_DX18"            
-# [28] "I10_DX19"             "I10_DX20"             "I10_DX21"            
-# [31] "I10_DX22"             "I10_DX23"             "I10_DX24"            
-# [34] "I10_DX25"             "I10_DX26"             "I10_DX27"            
-# [37] "I10_DX28"             "I10_NDX"              "I10_PROCTYPE"        
+# [10] "I10_DX1"              "I10_DX2"              "I10_DX3"
+# [13] "I10_DX4"              "I10_DX5"              "I10_DX6"
+# [16] "I10_DX7"              "I10_DX8"              "I10_DX9"
+# [19] "I10_DX10"             "I10_DX11"             "I10_DX12"
+# [22] "I10_DX13"             "I10_DX14"             "I10_DX15"
+# [25] "I10_DX16"             "I10_DX17"             "I10_DX18"
+# [28] "I10_DX19"             "I10_DX20"             "I10_DX21"
+# [31] "I10_DX22"             "I10_DX23"             "I10_DX24"
+# [34] "I10_DX25"             "I10_DX26"             "I10_DX27"
+# [37] "I10_DX28"             "I10_NDX"              "I10_PROCTYPE"
 
 ```
 
 Next we will select July as our month of interest to further reduce the size of the data and to focus on a time frame where we know fires took place in Oregon. We will also load in our environmental data files we made above from amadeus.
 
 ```{r eval=FALSE}
 # subset data to July
-july_subset_hcup_data <- subset_data[subset_data$AMONTH == 7,]
+july_subset_hcup_data <- subset_data[subset_data$AMONTH == 7, ]
 
 # load in amadeus files we made previously
 avg_smoke_density <- readRDS("smoke_density_avg_byZip.R")
@@ -331,13 +331,13 @@ total_smoke_density <- readRDS("smoke_density_total_byZip.R")
 We will now merge our environmental data into our hospital discharge (HCUP) data using an inner join on ZIP codes present in both datasets.
 
 ```{r eval=FALSE}
-# Perform an inner join to merge `july_subset_hcup_data` with 
-# `avg_smoke_density` based on the ZIP code (`ZIP` in HCUP data and 
+# Perform an inner join to merge `july_subset_hcup_data` with
+# `avg_smoke_density` based on the ZIP code (`ZIP` in HCUP data and
 # `ZCTA5CE10` in smoke density data)
 merged_data <- inner_join(july_subset_hcup_data, avg_smoke_density,
                           by = c("ZIP" = "ZCTA5CE10"))
 
-# Perform another inner join to add `total_smoke_density` to the existing 
+# Perform another inner join to add `total_smoke_density` to the existing
 # `merged_data`
 merged_data <- inner_join(merged_data, total_smoke_density,
                           by = c("ZIP" = "ZCTA5CE10"))
@@ -391,30 +391,30 @@ Finally, we fit a logistic regression model to examine the relationship between
 ```{r eval=FALSE}
 # Fit a logistic regression model with asthma diagnosis as the outcome variable
 # and different smoke exposure levels as predictors
-model <- glm(has_asthma ~ avg_light + avg_medium + avg_heavy, 
+model <- glm(has_asthma ~ avg_light + avg_medium + avg_heavy,
              data = smoke_summary, family = binomial)
 
 # Display model summary
 summary(model)
 # Call:
-# glm(formula = has_asthma ~ avg_light + avg_medium + avg_heavy, 
+# glm(formula = has_asthma ~ avg_light + avg_medium + avg_heavy,
 #     family = binomial, data = smoke_summary)
-# 
+#
 # Coefficients:
-#             Estimate Std. Error z value Pr(>|z|)    
+#             Estimate Std. Error z value Pr(>|z|)
 # (Intercept) -3.38823    0.09077 -37.329  < 2e-16 ***
-# avg_light   -0.21258    0.30322  -0.701    0.483    
+# avg_light   -0.21258    0.30322  -0.701    0.483
 # avg_medium   1.74996    0.32456   5.392 6.98e-08 ***
 # avg_heavy    1.82572    0.16826  10.850  < 2e-16 ***
 # ---
 # Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
-# 
+#
 # (Dispersion parameter for binomial family taken to be 1)
-# 
+#
 #     Null deviance: 42004  on 111124  degrees of freedom
 # Residual deviance: 41674  on 111121  degrees of freedom
 # AIC: 41682
-# 
+#
 # Number of Fisher Scoring iterations: 6
 ```