linear model

week1/citibike.R

@@ -19,30 +19,47 @@ trips <- mutate(trips, gender = factor(gender, levels=c(0,1,2), labels = c("Unkn
 
 
 ########################################
-# YOUR SOLUTIONS BELOW
+# YOUR SOLUTIONS BELOW 
 ########################################
 
-# count the number of trips (= rows in the data frame)
+# count the number of trips (= rows in the data frame) 224736, summarize(trips, count = n()) 
 
-# find the earliest and latest birth years (see help for max and min to deal with NAs)
+# find the earliest and latest birth years (see help for max and min to deal with NAs) 1997  as.numeric(trips$birth_year) then get min(birth_year na.rm=TRUE) 1899 
 
-# use filter and grepl to find all trips that either start or end on broadway
+# use filter and grepl to find all trips that either start or end on broadway filter(trips, grepl('Broadway', start_station_name) | grepl('Broadway', end_station_name))
 
-# do the same, but find all trips that both start and end on broadway
+# do the same, but find all trips that both start and end on broadway filter(trips, grepl('Broadway', start_station_name) , grepl('Broadway', end_station_name))
 
-# find all unique station names
+# find all unique station names trips |> distinct(start_station_name)
 
 # count the number of trips by gender, the average trip time by gender, and the standard deviation in trip time by gender
-# do this all at once, by using summarize() with multiple arguments
+# do this all at once, by using summarize() with multiple arguments 
+#gender   count avg_trip_time sd_trip_time
+ # <fct>    <int>         <dbl>        <dbl>
+#1 Unknown   6731         1741.        5566.
+#2 Male    176526          814.        5021.
+#3 Female   41479          991.        7115.
 
-# find the 10 most frequent station-to-station trips
+# find the 10 most frequent station-to-station trips 
+View(trips |> group_by(start_station_name, end_station_name) |>
+       summarize(count = n()) |>
+       arrange(desc(count) |>
+       head(n=10)))
 
-# find the top 3 end stations for trips starting from each start station
+# find the top 3 end stations for trips starting from each start station view( trips |> group_by(start_station_name, end_station_name) |> summarize(count = n()) |> group_by(start_station_name) |> arrange(desc(count)) |> mutate(rank = row_number()) |> filter(rank <=3))
 
-# find the top 3 most common station-to-station trips by gender
+# find the top 3 most common station-to-station trips by gender view(trips |> group_by(start_station_name, end_station_name, gender) |> summarize(count = n()) |> arrange(desc(count))|> group_by(gender) |> mutate(rank = row_number()) |> filter(rank <=3) |> arrange(gender))
 
 # find the day with the most trips
-# tip: first add a column for year/month/day without time of day (use as.Date or floor_date from the lubridate package)
+# tip: first add a column for year/month/day without time of day (use as.Date or floor_date from the lubridate package) trips_date <- trips |> mutate(date = as.Date(trips$starttime, "%m/%d/%y"))
+#view( trips_date |> group_by(date) |> summarize(count = n()) |> arrange(desc(count)) |> head(n=1) )
+
 
 # compute the average number of trips taken during each of the 24 hours of the day across the entire month
+trips_hours <- trips |> mutate(hour = hour(trips$starttime))
+view( trips_hours |> group_by(hour) |> summarize(count=n(), mean=count/28)) #you could also do days_in_month(trips$starttime) or something for each month
 # what time(s) of day tend to be peak hour(s)?
+trips_hours <- trips |> mutate(hour = hour(trips$starttime))
+view(trips_hours)
+view( trips_hours |> group_by(hour) |> summarize(count=n()) |> arrange(desc(count)))
+

week1/citibike.sh

@@ -3,21 +3,201 @@
 # add your solution after each of the 10 comments below
 #
 
-# count the number of unique stations
+# count the number of unique stations, 330  cut -d, -f9 201402-citibike-tripdata.csv | sort | uniq -c | wc -l
 
-# count the number of unique bikes
+# count the number of unique bikes cut -d, -f12 201402-citibike-tripdata.csv | sort | uniq -c | wc -l
+#5700
 
-# count the number of trips per day
+# count the number of trips per day cut -d, -f2 201402-citibike-tripdata.csv | cut -d' ' -f1 | sort | uniq -c
+#   12771 2014-02-01
+#   13816 2014-02-02
+#    2600 2014-02-03
+#    8709 2014-02-04
+#    2746 2014-02-05
+#    7196 2014-02-06
+#    8495 2014-02-07
+#    5986 2014-02-08
+#    4996 2014-02-09
+#    6846 2014-02-10
+#    8343 2014-02-11
+#    8580 2014-02-12
+#     876 2014-02-13
+#    3609 2014-02-14
+#    2261 2014-02-15
+#    3003 2014-02-16
+#    4854 2014-02-17
+#    5140 2014-02-18
+#    8506 2014-02-19
+#   11792 2014-02-20
+#    8680 2014-02-21
+#   13044 2014-02-22
+#   13324 2014-02-23
+#   12922 2014-02-24
+#   12830 2014-02-25
+#   11188 2014-02-26
+#   12036 2014-02-27
+#    9587 2014-02-28
+#       1 starttime
 
-# find the day with the most rides
+# find the day with the most rides cut -d, -f2 201402-citibike-tripdata.csv | cut -d' ' -f1 | sort | uniq -c | sort -nr | head -n1
+# 13816 2014-02-02
 
-# find the day with the fewest rides
+# find the day with the fewest rides  cut -d, -f2 201402-citibike-tripdata.csv | cut -d' ' -f1 | sort | uniq -c | sort | head -n2
+    #   1 starttime
+    # 876 2014-02-13
 
-# find the id of the bike with the most rides
+# find the id of the bike with the most rides: cut -d, -f12 201402-citibike-tripdata.csv | sort | uniq -c | sort -r | head -n1
+#    130 20837
 
 # count the number of rides by gender and birth year
+# cut -d, -f14,15 201402-citibike-tripdata.csv | sort | uniq -c
+#    6717 \N,0
+#       9 1899,1
+#      68 1900,1
+#      11 1901,1
+#       5 1907,1
+#       4 1910,1
+#       1 1913,1
+#       3 1917,1
+#       1 1921,1
+#      32 1922,1
+#       5 1926,2
+#       2 1927,1
+#       1 1932,1
+#       7 1932,2
+#      10 1933,1
+#      21 1934,1
+#      14 1935,1
+#      31 1936,1
+#      24 1937,1
+#      70 1938,1
+#       5 1938,2
+#      24 1939,1
+#      19 1939,2
+#      83 1940,1
+#       1 1940,2
+#     148 1941,1
+#      16 1941,2
+#     173 1942,1
+#       9 1942,2
+#     108 1943,1
+#      22 1943,2
+#     277 1944,1
+#      34 1944,2
+#     171 1945,1
+#      43 1945,2
+#     424 1946,1
+#      30 1946,2
+#     391 1947,1
+#      60 1947,2
+#     664 1948,1
+#     143 1948,2
+#     624 1949,1
+#     101 1949,2
+#     738 1950,1
+#     152 1950,2
+#       6 1951,0
+#    1006 1951,1
+#     146 1951,2
+#    1040 1952,1
+#     143 1952,2
+#    1474 1953,1
+#     301 1953,2
+#    1636 1954,1
+#     306 1954,2
+#    1568 1955,1
+#     349 1955,2
+#    1777 1956,1
+#     542 1956,2
+#    1676 1957,1
+#     562 1957,2
+#    2333 1958,1
+#     643 1958,2
+#    2281 1959,1
+#     539 1959,2
+#    2679 1960,1
+#     776 1960,2
+#    2315 1961,1
+#     432 1961,2
+#    2808 1962,1
+#     833 1962,2
+#    3514 1963,1
+#     715 1963,2
+#    3679 1964,1
+#     570 1964,2
+#    2957 1965,1
+#     687 1965,2
+#    3440 1966,1
+#     565 1966,2
+#    4016 1967,1
+#     634 1967,2
+#    3931 1968,1
+#     545 1968,2
+#    4557 1969,1
+#     898 1969,2
+#    4657 1970,1
+#    1079 1970,2
+#    4132 1971,1
+#     791 1971,2
+#    4066 1972,1
+#     962 1972,2
+#    4097 1973,1
+#     877 1973,2
+#    4957 1974,1
+#     891 1974,2
+#    4185 1975,1
+#     699 1975,2
+#    4557 1976,1
+#    1022 1976,2
+#    4817 1977,1
+#    1140 1977,2
+#    5645 1978,1
+#    1231 1978,2
+#    6433 1979,1
+#    1338 1979,2
+#    6173 1980,1
+#    1488 1980,2
+#    6620 1981,1
+#    1588 1981,2
+#    6244 1982,1
+#    1724 1982,2
+#    6890 1983,1
+#    1889 1983,2
+#    7348 1984,1
+#    1791 1984,2
+#    7043 1985,1
+#    2262 1985,2
+#    6147 1986,1
+#    1962 1986,2
+#    5776 1987,1
+#    1696 1987,2
+#    6449 1988,1
+#    1599 1988,2
+#    5408 1989,1
+#    1435 1989,2
+#    4541 1990,1
+#    1156 1990,2
+#       8 1991,0
+#    2377 1991,1
+#     689 1991,2
+#    1758 1992,1
+#     410 1992,2
+#    1398 1993,1
+#     289 1993,2
+#     927 1994,1
+#     288 1994,2
+#     664 1995,1
+#     163 1995,2
+#     234 1996,1
+#     100 1996,2
+#     164 1997,1
+#      87 1997,2
+#       1 birth year,gender
 
 # count the number of trips that start on cross streets that both contain numbers (e.g., "1 Ave & E 15 St", "E 39 St & 2 Ave", ...)
+# cut -d, -f5 201402-citibike-tripdata.csv | grep '.*[0-9].*&.*[0-9]' | wc -l
+#   90549
 
-
-# compute the average trip duration
+# compute the average trip duration (need awk)
+#awk '{SUM+=$1} END {print SUM/NR}' 201402-citibike-tripdata.csv
+#874.516