# Suppose we wanted to extract the rows of the chicago data frame where the levels of PM2.5 are greater than 30 (which is a reasonably high level), we could do

library(dplyr)
chicago <- readRDS("./chicago.rds")

chic.f <- filter(chicago, pm25tmean2 > 30)
str(chic.f)

'data.frame':	194 obs. of  8 variables:
 $ city      : chr  "chic" "chic" "chic" "chic" ...
 $ tmpd      : num  23 28 55 59 57 57 75 61 73 78 ...
 $ dptp      : num  21.9 25.8 51.3 53.7 52 56 65.8 59 60.3 67.1 ...
 $ date      : Date, format: "1998-01-17" "1998-01-23" ...
 $ pm25tmean2: num  38.1 34 39.4 35.4 33.3 ...
 $ pm10tmean2: num  32.5 38.7 34 28.5 35 ...
 $ o3tmean2  : num  3.18 1.75 10.79 14.3 20.66 ...
 $ no2tmean2 : num  25.3 29.4 25.3 31.4 26.8 ...

# Looking at the first three and last three rows shows the dates in descending order.

head(select(chicago, date, pm25tmean2), 3)
tail(select(chicago, date, pm25tmean2), 3)

# First, we can create a year varible using as.POSIXlt().

chicago <- mutate(chicago, year = as.POSIXlt(date)$year + 1900)

# Now we can create a separate data frame that splits the original data frame by year.

years <- group_by(chicago, year)
chicago

# Finally, we compute summary statistics for each year in the data frame with the summarize() function.

summarize(years, pm25 = mean(pm25, na.rm = TRUE), 
           o3 = max(o3tmean2, na.rm = TRUE), 
           no2 = median(no2tmean2, na.rm = TRUE))

# summarize() returns a data frame with year as the first column, and then the annual averages of pm25, o3, and no2.

# In a slightly more complicated example, we might want to know what the average levels of ozone (o3) and nitrogen dioxide (no2) within quintiles of pm25 are. A slicker way to do this would be through a regression model, but we can actually do this quickly with group_by() and summarize().

# First, we can create a categorical variable of pm25 divided into quintiles.

qq <- quantile(chicago$pm25, seq(0, 1, 0.2), na.rm = TRUE)
chicago <- mutate(chicago, pm25.quint = cut(pm25, qq))
chicago

# Now we can group the data frame by the pm25.quint variable.

quint <- group_by(chicago, pm25.quint)

# Finally, we can compute the mean of o3 and no2 within quintiles of pm25.

summarize(quint, o3 = mean(o3tmean2, na.rm = TRUE), 
           no2 = mean(no2tmean2, na.rm = TRUE))
# A tibble: 6 × 3

# From the table, it seems there isn’t a strong relationship between pm25 and o3, but there appears to be a positive correlation between pm25 and no2. More sophisticated statistical modeling can help to provide precise answers to these questions, but a simple application of dplyr functions can often get you most of the way there.

# You can group by expressions: this is just short-hand for a mutate/rename followed by a simple group_by

mtcars %>% group_by(vsam = vs + am)

# Newly created variables are available immediately
mtcars %>% as_tibble() %>% mutate(
cyl2 = cyl * 2,
cyl4 = cyl2 * 2
)

# You can also use mutate() to remove variables and
# modify existing variables
mtcars %>% as_tibble() %>% mutate(
mpg = NULL,
disp = disp * 0.0163871 # convert to litres
)


# window functions are useful for grouped mutates
mtcars %>%
group_by(cyl) %>%
mutate(rank = min_rank(desc(mpg)))
# see `vignette("window-functions")` for more details

# You can drop variables by setting them to NULL
mtcars %>% mutate(cyl = NULL)

# mutate() vs transmute --------------------------
# mutate() keeps all existing variables
mtcars %>%
mutate(displ_l = disp / 61.0237)

# transmute keeps only the variables you create
mtcars %>%
transmute(displ_l = disp / 61.0237)


# mutate() supports quasiquotation. You can unquote quosures, which
# can refer to both contextual variables and variable names:
var <- 100
as_tibble(mtcars) %>% mutate(cyl = !!quo(cyl * var))

library(dplyr)
chicago <- readRDS("./chicago.rds")
chicago <- rename(chicago, dewpoint = dptp, pm25 = pm25tmean2)

# Here we create a pm25detrend variable that subtracts the mean from the pm25 variable.

chicago <- mutate(chicago, pm25detrend = pm25 - mean(pm25, na.rm = TRUE))
head(chicago)

Attaching package: ‘dplyr’

The following objects are masked from ‘package:stats’:

    filter, lag

The following objects are masked from ‘package:base’:

    intersect, setdiff, setequal, union

mutate(airquality, new = -Ozone, Temp = (Temp - 32) / 1.8)

library(dplyr)
chicago <- readRDS("./chicago.rds")
chicago <- rename(chicago, dewpoint = dptp, pm25 = pm25tmean2)

qq <- quantile(chicago$pm25, seq(0, 1, 0.2), na.rm = TRUE)
chicago <- mutate(chicago, pm25.quint = cut(pm25, qq))

mutate(chicago, pm25.quint = cut(pm25, qq)) %>%    
         group_by(pm25.quint) %>% 
         summarize(o3 = mean(o3tmean2, na.rm = TRUE), 
                   no2 = mean(no2tmean2, na.rm = TRUE))

#Another example might be computing the average pollutant level by month. This could be useful to see if there are any seasonal trends in the data.

mutate(chicago, month = as.POSIXlt(date)$mon + 1) %>% 
         group_by(month) %>% 
         summarize(pm25 = mean(pm25, na.rm = TRUE), 
                   o3 = max(o3tmean2, na.rm = TRUE), 
                   no2 = median(no2tmean2, na.rm = TRUE))
# A tibble: 12 × 4

# Here we can see that o3 tends to be low in the winter months and high in the summer while no2 is higher in the winter and lower in the summer.

# Here you can see the names of the first five variables in the chicago data frame.

library(dplyr)
chicago <- readRDS("./chicago.rds")

head(chicago[, 1:5], 3)

# The dptp column is supposed to represent the dew point temperature adn the pm25tmean2 column provides the PM2.5 data. However, these names are pretty obscure or awkward and probably be renamed to something more sensible.

chicago <- rename(chicago, dewpoint = dptp, pm25 = pm25tmean2)
head(chicago[, 1:5], 3)

# The syntax inside the rename() function is to have the new name on the left-hand side of the = sign and the old name on the right-hand side.

# The select() function also allows a special syntax that allows you to specify variable names based on patterns. So, for example, if you wanted to keep every variable that ends with a “2”, we could do

subset <- select(chicago, ends_with("2"))
str(subset)

'data.frame':	6940 obs. of  4 variables:
 $ pm25tmean2: num  NA NA NA NA NA NA NA NA NA NA ...
 $ pm10tmean2: num  34 NA 34.2 47 NA ...
 $ o3tmean2  : num  4.25 3.3 3.33 4.38 4.75 ...
 $ no2tmean2 : num  20 23.2 23.8 30.4 30.3 ...

mtcars$model <- rownames(mtcars)
first <- mtcars[1:20, ]
second <- mtcars[10:32, ]
first

second

intersect(first, second)

union(first, second)

setdiff(first, second)

# Each summary call removes one grouping level (since that group is now just a single row)

mtcars %>%
group_by(cyl, vs) %>%
summarise(cyl_n = n()) %>%
group_vars()

# Note that with data frames, newly created summaries immediately overwrite existing variables

mtcars %>%
group_by(cyl) %>%
summarise(disp = mean(disp), sd = sd(disp))

date	pm25tmean2
2005-12-31	15.00000
2005-12-30	15.05714
2005-12-29	7.45000

city	tmpd	dewpoint	date	pm25	pm10tmean2	o3tmean2	no2tmean2	year
chic	31.5	31.500	1987-01-01	NA	34.00000	4.250000	19.98810	1987
chic	33.0	29.875	1987-01-02	NA	NA	3.304348	23.19099	1987
chic	33.0	27.375	1987-01-03	NA	34.16667	3.333333	23.81548	1987
chic	29.0	28.625	1987-01-04	NA	47.00000	4.375000	30.43452	1987
chic	32.0	28.875	1987-01-05	NA	NA	4.750000	30.33333	1987
chic	40.0	35.125	1987-01-06	NA	48.00000	5.833333	25.77233	1987
chic	34.5	26.750	1987-01-07	NA	41.00000	9.291667	20.58171	1987
chic	29.0	22.000	1987-01-08	NA	36.00000	11.291667	17.03723	1987
chic	26.5	29.000	1987-01-09	NA	33.28571	4.500000	23.38889	1987
chic	32.5	27.750	1987-01-10	NA	NA	4.958333	19.54167	1987
chic	29.5	20.125	1987-01-11	NA	22.00000	17.541667	13.70139	1987
chic	34.5	26.000	1987-01-12	NA	26.00000	8.000000	33.02083	1987
chic	34.0	32.250	1987-01-13	NA	53.00000	4.958333	38.06142	1987
chic	37.5	36.375	1987-01-14	NA	43.00000	4.208333	32.19444	1987
chic	32.5	24.250	1987-01-15	NA	28.83333	4.458333	18.87131	1987
chic	25.0	21.500	1987-01-16	NA	19.00000	7.916667	19.46667	1987
chic	27.0	24.750	1987-01-17	NA	NA	5.833333	20.70833	1987
chic	17.5	11.125	1987-01-18	NA	39.00000	6.375000	21.03333	1987
chic	23.0	15.750	1987-01-19	NA	32.00000	14.875000	17.17409	1987
chic	20.5	11.500	1987-01-20	NA	38.00000	7.250000	21.61021	1987
chic	22.0	20.625	1987-01-21	NA	32.85714	8.913043	24.52083	1987
chic	19.5	7.375	1987-01-22	NA	52.00000	10.500000	16.98798	1987
chic	2.5	-12.250	1987-01-23	NA	55.00000	14.625000	14.66250	1987
chic	2.0	-5.625	1987-01-24	NA	38.00000	10.083333	18.69167	1987
chic	9.5	-5.250	1987-01-25	NA	NA	6.666667	26.30417	1987
chic	16.0	4.750	1987-01-26	NA	71.00000	4.583333	32.42143	1987
chic	17.5	17.750	1987-01-27	NA	39.33333	6.000000	30.69306	1987
chic	29.5	18.250	1987-01-28	NA	47.00000	6.875000	29.12943	1987
chic	29.5	32.875	1987-01-29	NA	35.00000	2.916667	28.14529	1987
chic	32.5	24.125	1987-01-30	NA	59.00000	8.791667	19.79861	1987
⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮
chic	19	8.5	2005-12-02	NA	19.50	9.156250	23.29167	2005
chic	25	19.0	2005-12-03	13.34286	20.00	10.333333	25.19444	2005
chic	20	15.8	2005-12-04	15.30000	15.50	13.177083	21.70833	2005
chic	11	2.8	2005-12-05	NA	30.00	6.447917	28.38889	2005
chic	11	3.2	2005-12-06	24.61667	33.00	4.701540	29.08333	2005
chic	8	-1.8	2005-12-07	37.80000	39.00	3.916214	34.30952	2005
chic	16	15.6	2005-12-08	24.30000	31.00	5.995265	34.22222	2005
chic	20	10.9	2005-12-09	25.45000	22.00	5.958333	31.41667	2005
chic	22	16.2	2005-12-10	18.20000	30.00	9.135417	28.70833	2005
chic	20	17.2	2005-12-11	10.60000	14.00	11.333333	22.55556	2005
chic	19	11.6	2005-12-12	19.22500	28.75	5.031250	39.74621	2005
chic	26	19.8	2005-12-13	26.50000	21.00	6.628623	29.56944	2005
chic	32	27.4	2005-12-14	26.90000	16.00	3.802083	30.63384	2005
chic	30	27.9	2005-12-15	14.40000	16.50	4.895833	25.43056	2005
chic	21	14.7	2005-12-16	11.00000	22.00	11.166667	16.87500	2005
chic	16	7.3	2005-12-17	13.80000	20.00	8.593750	20.73611	2005
chic	10	1.9	2005-12-18	12.20000	17.50	13.552083	19.11111	2005
chic	5	-0.3	2005-12-19	21.15000	21.00	8.058877	31.79167	2005
chic	13	7.7	2005-12-20	25.75000	32.00	3.849185	32.89773	2005
chic	12	7.7	2005-12-21	37.92857	59.50	3.663949	34.86111	2005
chic	22	23.3	2005-12-22	36.65000	42.50	5.385417	33.73026	2005
chic	41	32.6	2005-12-23	32.90000	34.50	6.906250	29.08333	2005
chic	37	35.2	2005-12-24	30.77143	25.20	1.770833	31.98611	2005
chic	35	32.1	2005-12-25	6.70000	8.00	14.354167	13.79167	2005
chic	35	29.6	2005-12-26	8.40000	8.50	14.041667	16.81944	2005
chic	40	33.6	2005-12-27	23.56000	27.00	4.468750	23.50000	2005
chic	37	34.5	2005-12-28	17.75000	27.50	3.260417	19.28563	2005
chic	35	29.4	2005-12-29	7.45000	23.50	6.794837	19.97222	2005
chic	36	31.0	2005-12-30	15.05714	19.20	3.034420	22.80556	2005
chic	35	30.1	2005-12-31	15.00000	23.50	2.531250	13.25000	2005

year	pm25	o3	no2
1987	NaN	62.96966	23.49369
1988	NaN	61.67708	24.52296
1989	NaN	59.72727	26.14062
1990	NaN	52.22917	22.59583
1991	NaN	63.10417	21.38194
1992	NaN	50.82870	24.78921
1993	NaN	44.30093	25.76993
1994	NaN	52.17844	28.47500
1995	NaN	66.58750	27.26042
1996	NaN	58.39583	26.38715
1997	NaN	56.54167	25.48143
1998	18.26467	50.66250	24.58649
1999	18.49646	57.48864	24.66667
2000	16.93806	55.76103	23.46082
2001	16.92632	51.81984	25.06522
2002	15.27335	54.88043	22.73750
2003	15.23183	56.16608	24.62500
2004	14.62864	44.48240	23.39130
2005	16.18556	58.84126	22.62387

city	tmpd	dewpoint	date	pm25	pm10tmean2	o3tmean2	no2tmean2	year	pm25.quint
chic	31.5	31.500	1987-01-01	NA	34.00000	4.250000	19.98810	1987	NA
chic	33.0	29.875	1987-01-02	NA	NA	3.304348	23.19099	1987	NA
chic	33.0	27.375	1987-01-03	NA	34.16667	3.333333	23.81548	1987	NA
chic	29.0	28.625	1987-01-04	NA	47.00000	4.375000	30.43452	1987	NA
chic	32.0	28.875	1987-01-05	NA	NA	4.750000	30.33333	1987	NA
chic	40.0	35.125	1987-01-06	NA	48.00000	5.833333	25.77233	1987	NA
chic	34.5	26.750	1987-01-07	NA	41.00000	9.291667	20.58171	1987	NA
chic	29.0	22.000	1987-01-08	NA	36.00000	11.291667	17.03723	1987	NA
chic	26.5	29.000	1987-01-09	NA	33.28571	4.500000	23.38889	1987	NA
chic	32.5	27.750	1987-01-10	NA	NA	4.958333	19.54167	1987	NA
chic	29.5	20.125	1987-01-11	NA	22.00000	17.541667	13.70139	1987	NA
chic	34.5	26.000	1987-01-12	NA	26.00000	8.000000	33.02083	1987	NA
chic	34.0	32.250	1987-01-13	NA	53.00000	4.958333	38.06142	1987	NA
chic	37.5	36.375	1987-01-14	NA	43.00000	4.208333	32.19444	1987	NA
chic	32.5	24.250	1987-01-15	NA	28.83333	4.458333	18.87131	1987	NA
chic	25.0	21.500	1987-01-16	NA	19.00000	7.916667	19.46667	1987	NA
chic	27.0	24.750	1987-01-17	NA	NA	5.833333	20.70833	1987	NA
chic	17.5	11.125	1987-01-18	NA	39.00000	6.375000	21.03333	1987	NA
chic	23.0	15.750	1987-01-19	NA	32.00000	14.875000	17.17409	1987	NA
chic	20.5	11.500	1987-01-20	NA	38.00000	7.250000	21.61021	1987	NA
chic	22.0	20.625	1987-01-21	NA	32.85714	8.913043	24.52083	1987	NA
chic	19.5	7.375	1987-01-22	NA	52.00000	10.500000	16.98798	1987	NA
chic	2.5	-12.250	1987-01-23	NA	55.00000	14.625000	14.66250	1987	NA
chic	2.0	-5.625	1987-01-24	NA	38.00000	10.083333	18.69167	1987	NA
chic	9.5	-5.250	1987-01-25	NA	NA	6.666667	26.30417	1987	NA
chic	16.0	4.750	1987-01-26	NA	71.00000	4.583333	32.42143	1987	NA
chic	17.5	17.750	1987-01-27	NA	39.33333	6.000000	30.69306	1987	NA
chic	29.5	18.250	1987-01-28	NA	47.00000	6.875000	29.12943	1987	NA
chic	29.5	32.875	1987-01-29	NA	35.00000	2.916667	28.14529	1987	NA
chic	32.5	24.125	1987-01-30	NA	59.00000	8.791667	19.79861	1987	NA
⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮
chic	19	8.5	2005-12-02	NA	19.50	9.156250	23.29167	2005	NA
chic	25	19.0	2005-12-03	13.34286	20.00	10.333333	25.19444	2005	(12.4,16.7]
chic	20	15.8	2005-12-04	15.30000	15.50	13.177083	21.70833	2005	(12.4,16.7]
chic	11	2.8	2005-12-05	NA	30.00	6.447917	28.38889	2005	NA
chic	11	3.2	2005-12-06	24.61667	33.00	4.701540	29.08333	2005	(22.6,61.5]
chic	8	-1.8	2005-12-07	37.80000	39.00	3.916214	34.30952	2005	(22.6,61.5]
chic	16	15.6	2005-12-08	24.30000	31.00	5.995265	34.22222	2005	(22.6,61.5]
chic	20	10.9	2005-12-09	25.45000	22.00	5.958333	31.41667	2005	(22.6,61.5]
chic	22	16.2	2005-12-10	18.20000	30.00	9.135417	28.70833	2005	(16.7,22.6]
chic	20	17.2	2005-12-11	10.60000	14.00	11.333333	22.55556	2005	(8.7,12.4]
chic	19	11.6	2005-12-12	19.22500	28.75	5.031250	39.74621	2005	(16.7,22.6]
chic	26	19.8	2005-12-13	26.50000	21.00	6.628623	29.56944	2005	(22.6,61.5]
chic	32	27.4	2005-12-14	26.90000	16.00	3.802083	30.63384	2005	(22.6,61.5]
chic	30	27.9	2005-12-15	14.40000	16.50	4.895833	25.43056	2005	(12.4,16.7]
chic	21	14.7	2005-12-16	11.00000	22.00	11.166667	16.87500	2005	(8.7,12.4]
chic	16	7.3	2005-12-17	13.80000	20.00	8.593750	20.73611	2005	(12.4,16.7]
chic	10	1.9	2005-12-18	12.20000	17.50	13.552083	19.11111	2005	(8.7,12.4]
chic	5	-0.3	2005-12-19	21.15000	21.00	8.058877	31.79167	2005	(16.7,22.6]
chic	13	7.7	2005-12-20	25.75000	32.00	3.849185	32.89773	2005	(22.6,61.5]
chic	12	7.7	2005-12-21	37.92857	59.50	3.663949	34.86111	2005	(22.6,61.5]
chic	22	23.3	2005-12-22	36.65000	42.50	5.385417	33.73026	2005	(22.6,61.5]
chic	41	32.6	2005-12-23	32.90000	34.50	6.906250	29.08333	2005	(22.6,61.5]
chic	37	35.2	2005-12-24	30.77143	25.20	1.770833	31.98611	2005	(22.6,61.5]
chic	35	32.1	2005-12-25	6.70000	8.00	14.354167	13.79167	2005	(1.7,8.7]
chic	35	29.6	2005-12-26	8.40000	8.50	14.041667	16.81944	2005	(1.7,8.7]
chic	40	33.6	2005-12-27	23.56000	27.00	4.468750	23.50000	2005	(22.6,61.5]
chic	37	34.5	2005-12-28	17.75000	27.50	3.260417	19.28563	2005	(16.7,22.6]
chic	35	29.4	2005-12-29	7.45000	23.50	6.794837	19.97222	2005	(1.7,8.7]
chic	36	31.0	2005-12-30	15.05714	19.20	3.034420	22.80556	2005	(12.4,16.7]
chic	35	30.1	2005-12-31	15.00000	23.50	2.531250	13.25000	2005	(12.4,16.7]

pm25.quint	o3	no2
(1.7,8.7]	21.66401	17.99129
(8.7,12.4]	20.38248	22.13004
(12.4,16.7]	20.66160	24.35708
(16.7,22.6]	19.88122	27.27132
(22.6,61.5]	20.31775	29.64427
NA	18.79044	25.77585

R Programming & Statistics Notes

Chapter 2.2.1.1 Exercises

mpg	cyl	disp	hp	drat	wt	qsec	vs	am	gear	carb	vsam
21.0	6	160.0	110	3.90	2.620	16.46	0	1	4	4	1
21.0	6	160.0	110	3.90	2.875	17.02	0	1	4	4	1
22.8	4	108.0	93	3.85	2.320	18.61	1	1	4	1	2
21.4	6	258.0	110	3.08	3.215	19.44	1	0	3	1	1
18.7	8	360.0	175	3.15	3.440	17.02	0	0	3	2	0
18.1	6	225.0	105	2.76	3.460	20.22	1	0	3	1	1
14.3	8	360.0	245	3.21	3.570	15.84	0	0	3	4	0
24.4	4	146.7	62	3.69	3.190	20.00	1	0	4	2	1
22.8	4	140.8	95	3.92	3.150	22.90	1	0	4	2	1
19.2	6	167.6	123	3.92	3.440	18.30	1	0	4	4	1
17.8	6	167.6	123	3.92	3.440	18.90	1	0	4	4	1
16.4	8	275.8	180	3.07	4.070	17.40	0	0	3	3	0
17.3	8	275.8	180	3.07	3.730	17.60	0	0	3	3	0
15.2	8	275.8	180	3.07	3.780	18.00	0	0	3	3	0
10.4	8	472.0	205	2.93	5.250	17.98	0	0	3	4	0
10.4	8	460.0	215	3.00	5.424	17.82	0	0	3	4	0
14.7	8	440.0	230	3.23	5.345	17.42	0	0	3	4	0
32.4	4	78.7	66	4.08	2.200	19.47	1	1	4	1	2
30.4	4	75.7	52	4.93	1.615	18.52	1	1	4	2	2
33.9	4	71.1	65	4.22	1.835	19.90	1	1	4	1	2
21.5	4	120.1	97	3.70	2.465	20.01	1	0	3	1	1
15.5	8	318.0	150	2.76	3.520	16.87	0	0	3	2	0
15.2	8	304.0	150	3.15	3.435	17.30	0	0	3	2	0
13.3	8	350.0	245	3.73	3.840	15.41	0	0	3	4	0
19.2	8	400.0	175	3.08	3.845	17.05	0	0	3	2	0
27.3	4	79.0	66	4.08	1.935	18.90	1	1	4	1	2
26.0	4	120.3	91	4.43	2.140	16.70	0	1	5	2	1
30.4	4	95.1	113	3.77	1.513	16.90	1	1	5	2	2
15.8	8	351.0	264	4.22	3.170	14.50	0	1	5	4	1
19.7	6	145.0	175	3.62	2.770	15.50	0	1	5	6	1
15.0	8	301.0	335	3.54	3.570	14.60	0	1	5	8	1
21.4	4	121.0	109	4.11	2.780	18.60	1	1	4	2	2

cyl	disp	hp	drat	wt	qsec	vs	am	gear	carb
6	2.621936	110	3.90	2.620	16.46	0	1	4	4
6	2.621936	110	3.90	2.875	17.02	0	1	4	4
4	1.769807	93	3.85	2.320	18.61	1	1	4	1
6	4.227872	110	3.08	3.215	19.44	1	0	3	1
8	5.899356	175	3.15	3.440	17.02	0	0	3	2
6	3.687098	105	2.76	3.460	20.22	1	0	3	1
8	5.899356	245	3.21	3.570	15.84	0	0	3	4
4	2.403988	62	3.69	3.190	20.00	1	0	4	2
4	2.307304	95	3.92	3.150	22.90	1	0	4	2
6	2.746478	123	3.92	3.440	18.30	1	0	4	4
6	2.746478	123	3.92	3.440	18.90	1	0	4	4
8	4.519562	180	3.07	4.070	17.40	0	0	3	3
8	4.519562	180	3.07	3.730	17.60	0	0	3	3
8	4.519562	180	3.07	3.780	18.00	0	0	3	3
8	7.734711	205	2.93	5.250	17.98	0	0	3	4
8	7.538066	215	3.00	5.424	17.82	0	0	3	4
8	7.210324	230	3.23	5.345	17.42	0	0	3	4
4	1.289665	66	4.08	2.200	19.47	1	1	4	1
4	1.240503	52	4.93	1.615	18.52	1	1	4	2
4	1.165123	65	4.22	1.835	19.90	1	1	4	1
4	1.968091	97	3.70	2.465	20.01	1	0	3	1
8	5.211098	150	2.76	3.520	16.87	0	0	3	2
8	4.981678	150	3.15	3.435	17.30	0	0	3	2
8	5.735485	245	3.73	3.840	15.41	0	0	3	4
8	6.554840	175	3.08	3.845	17.05	0	0	3	2
4	1.294581	66	4.08	1.935	18.90	1	1	4	1
4	1.971368	91	4.43	2.140	16.70	0	1	5	2
4	1.558413	113	3.77	1.513	16.90	1	1	5	2
8	5.751872	264	4.22	3.170	14.50	0	1	5	4
6	2.376130	175	3.62	2.770	15.50	0	1	5	6
8	4.932517	335	3.54	3.570	14.60	0	1	5	8
4	1.982839	109	4.11	2.780	18.60	1	1	4	2

Ozone	Solar.R	Wind	Temp	Month	Day	new
41	190	7.4	19.44444	5	1	-41
36	118	8.0	22.22222	5	2	-36
12	149	12.6	23.33333	5	3	-12
18	313	11.5	16.66667	5	4	-18
NA	NA	14.3	13.33333	5	5	NA
28	NA	14.9	18.88889	5	6	-28
23	299	8.6	18.33333	5	7	-23
19	99	13.8	15.00000	5	8	-19
8	19	20.1	16.11111	5	9	-8
NA	194	8.6	20.55556	5	10	NA
7	NA	6.9	23.33333	5	11	-7
16	256	9.7	20.55556	5	12	-16
11	290	9.2	18.88889	5	13	-11
14	274	10.9	20.00000	5	14	-14
18	65	13.2	14.44444	5	15	-18
14	334	11.5	17.77778	5	16	-14
34	307	12.0	18.88889	5	17	-34
6	78	18.4	13.88889	5	18	-6
30	322	11.5	20.00000	5	19	-30
11	44	9.7	16.66667	5	20	-11
1	8	9.7	15.00000	5	21	-1
11	320	16.6	22.77778	5	22	-11
4	25	9.7	16.11111	5	23	-4
32	92	12.0	16.11111	5	24	-32
NA	66	16.6	13.88889	5	25	NA
NA	266	14.9	14.44444	5	26	NA
NA	NA	8.0	13.88889	5	27	NA
23	13	12.0	19.44444	5	28	-23
45	252	14.9	27.22222	5	29	-45
115	223	5.7	26.11111	5	30	-115
⋮	⋮	⋮	⋮	⋮	⋮	⋮
96	167	6.9	32.77778	9	1	-96
78	197	5.1	33.33333	9	2	-78
73	183	2.8	33.88889	9	3	-73
91	189	4.6	33.88889	9	4	-91
47	95	7.4	30.55556	9	5	-47
32	92	15.5	28.88889	9	6	-32
20	252	10.9	26.66667	9	7	-20
23	220	10.3	25.55556	9	8	-23
21	230	10.9	23.88889	9	9	-21
24	259	9.7	22.77778	9	10	-24
44	236	14.9	27.22222	9	11	-44
21	259	15.5	24.44444	9	12	-21
28	238	6.3	25.00000	9	13	-28
9	24	10.9	21.66667	9	14	-9
13	112	11.5	21.66667	9	15	-13
46	237	6.9	25.55556	9	16	-46
18	224	13.8	19.44444	9	17	-18
13	27	10.3	24.44444	9	18	-13
24	238	10.3	20.00000	9	19	-24
16	201	8.0	27.77778	9	20	-16
13	238	12.6	17.77778	9	21	-13
23	14	9.2	21.66667	9	22	-23
36	139	10.3	27.22222	9	23	-36
7	49	10.3	20.55556	9	24	-7
14	20	16.6	17.22222	9	25	-14
30	193	6.9	21.11111	9	26	-30
NA	145	13.2	25.00000	9	27	NA
14	191	14.3	23.88889	9	28	-14
18	131	8.0	24.44444	9	29	-18
20	223	11.5	20.00000	9	30	-20

month	pm25	o3	no2
1	17.76996	28.22222	25.35417
2	20.37513	37.37500	26.78034
3	17.40818	39.05000	26.76984
4	13.85879	47.94907	25.03125
5	14.07420	52.75000	24.22222
6	15.86461	66.58750	25.01140
7	16.57087	59.54167	22.38442
8	16.93380	53.96701	22.98333
9	15.91279	57.48864	24.47917
10	14.23557	47.09275	24.15217
11	15.15794	29.45833	23.56537
12	17.52221	27.70833	24.45773

	mpg	cyl	disp	hp	drat	wt	qsec	vs	am	gear	carb	model
Mazda RX4	21.0	6	160.0	110	3.90	2.620	16.46	0	1	4	4	Mazda RX4
Mazda RX4 Wag	21.0	6	160.0	110	3.90	2.875	17.02	0	1	4	4	Mazda RX4 Wag
Datsun 710	22.8	4	108.0	93	3.85	2.320	18.61	1	1	4	1	Datsun 710
Hornet 4 Drive	21.4	6	258.0	110	3.08	3.215	19.44	1	0	3	1	Hornet 4 Drive
Hornet Sportabout	18.7	8	360.0	175	3.15	3.440	17.02	0	0	3	2	Hornet Sportabout
Valiant	18.1	6	225.0	105	2.76	3.460	20.22	1	0	3	1	Valiant
Duster 360	14.3	8	360.0	245	3.21	3.570	15.84	0	0	3	4	Duster 360
Merc 240D	24.4	4	146.7	62	3.69	3.190	20.00	1	0	4	2	Merc 240D
Merc 230	22.8	4	140.8	95	3.92	3.150	22.90	1	0	4	2	Merc 230
Merc 280	19.2	6	167.6	123	3.92	3.440	18.30	1	0	4	4	Merc 280
Merc 280C	17.8	6	167.6	123	3.92	3.440	18.90	1	0	4	4	Merc 280C
Merc 450SE	16.4	8	275.8	180	3.07	4.070	17.40	0	0	3	3	Merc 450SE
Merc 450SL	17.3	8	275.8	180	3.07	3.730	17.60	0	0	3	3	Merc 450SL
Merc 450SLC	15.2	8	275.8	180	3.07	3.780	18.00	0	0	3	3	Merc 450SLC
Cadillac Fleetwood	10.4	8	472.0	205	2.93	5.250	17.98	0	0	3	4	Cadillac Fleetwood
Lincoln Continental	10.4	8	460.0	215	3.00	5.424	17.82	0	0	3	4	Lincoln Continental
Chrysler Imperial	14.7	8	440.0	230	3.23	5.345	17.42	0	0	3	4	Chrysler Imperial
Fiat 128	32.4	4	78.7	66	4.08	2.200	19.47	1	1	4	1	Fiat 128
Honda Civic	30.4	4	75.7	52	4.93	1.615	18.52	1	1	4	2	Honda Civic
Toyota Corolla	33.9	4	71.1	65	4.22	1.835	19.90	1	1	4	1	Toyota Corolla

displ_l
2.621932
2.621932
1.769804
4.227866
5.899347
3.687092
5.899347
2.403984
2.307300
2.746474
2.746474
4.519556
4.519556
4.519556
7.734700
7.538055
7.210313
1.289663
1.240502
1.165121
1.968088
5.211090
4.981671
5.735477
6.554830
1.294579
1.971365
1.558411
5.751864
2.376126
4.932510
1.982836

cyl	disp	sd
4	105.1364	NA
6	183.3143	NA
8	353.1000	NA