Как исправить ошибку неверного типа (списка) для целочисленной переменной в GAM - PullRequest
Новая
       6

Как исправить ошибку неверного типа (списка) для целочисленной переменной в GAM

1 голос
/ 11 марта 2020

Довольно базовая c проблема, в которой я даже не уверен, что это действительно проблема. У меня есть фрейм данных monthly_summary: 

structure(list(year = c(2015L, 2015L, 2013L, 2014L, 2016L, 2016L, 
2016L, 2016L, 2014L, 2014L, 2014L, 2015L, 2015L, 2015L, 2014L, 
2013L, 2014L, 2014L, 2015L, 2016L, 2014L, 2014L, 2015L, 2013L, 
2014L, 2014L, 2015L, 2015L, 2015L, 2016L, 2014L, 2014L, 2015L, 
2013L, 2013L, 2014L, 2014L, 2014L, 2014L, 2015L, 2015L, 2015L, 
2015L, 2016L, 2016L, 2016L, 2016L, 2017L, 2017L, 2015L, 2015L, 
2013L, 2013L, 2014L, 2014L, 2014L, 2015L, 2016L, 2016L, 2016L, 
2017L, 2014L, 2014L, 2015L, 2014L, 2014L, 2015L, 2015L, 2015L, 
2015L, 2016L, 2016L, 2016L, 2017L, 2017L, 2014L, 2014L, 2015L, 
2013L, 2014L, 2014L, 2015L, 2015L, 2016L, 2017L, 2015L, 2015L, 
2016L, 2017L), month = c(4L, 5L, 6L, 10L, 2L, 4L, 5L, 10L, 9L, 
3L, 9L, 3L, 6L, 11L, 9L, 9L, 3L, 10L, 3L, 6L, 3L, 9L, 2L, 11L, 
2L, 4L, 3L, 5L, 10L, 5L, 3L, 9L, 3L, 9L, 11L, 2L, 4L, 7L, 10L, 
2L, 4L, 8L, 10L, 2L, 3L, 6L, 9L, 3L, 6L, 3L, 4L, 9L, 11L, 3L, 
6L, 10L, 2L, 2L, 4L, 8L, 1L, 3L, 6L, 7L, 2L, 7L, 2L, 3L, 4L, 
5L, 3L, 4L, 5L, 3L, 10L, 2L, 7L, 3L, 10L, 3L, 5L, 2L, 12L, 2L, 
6L, 3L, 7L, 3L, 9L), EstimatedAge = c(-1, -1, -1, -1, -1, -1, 
-1, 2, 3, 4, 4, 5, 5, 6, 2, 2, 2, 2, 2, 2, 3, 3, 3, 3, 3, 3, 
3, 3, 3, 3, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 
4, 4, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 6, 6, 6, 6, 6, 6, 6, 
6, 6, 6, 6, 6, 6, 6, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 8, 8, 8, 8
), Species = structure(c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 
2L, 2L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L
), .Label = c("Catfish", "Largemouth Bass", "Striped Bass"), class = "factor"), 
    at_large = c(8L, 13L, 6L, 3L, 14L, 16L, 13L, 2L, 7L, 22L, 
    24L, 3L, 2L, 1L, 27L, 10L, 16L, 24L, 31L, 24L, 39L, 28L, 
    48L, 14L, 26L, 27L, 54L, 30L, 29L, 40L, 36L, 29L, 37L, 8L, 
    14L, 21L, 27L, 27L, 28L, 31L, 26L, 24L, 28L, 29L, 33L, 30L, 
    23L, 28L, 16L, 32L, 20L, 9L, 9L, 22L, 17L, 17L, 21L, 20L, 
    14L, 8L, 13L, 11L, 10L, 12L, 15L, 8L, 10L, 15L, 10L, 10L, 
    7L, 6L, 5L, 10L, 2L, 20L, 20L, 33L, 7L, 21L, 14L, 25L, 21L, 
    24L, 10L, 2L, 4L, 5L, 1L), Avg_Flow = c(559.1, 566.290322580645, 
    2047.8, 403.354838709677, 2152.03448275862, 764.6, 956.935483870968, 
    2887.16129032258, 2021.53333333333, 2055.93548387097, 2021.53333333333, 
    1228.58064516129, 398.766666666667, 649.8, 2021.53333333333, 
    3378.16666666667, 2055.93548387097, 403.354838709677, 1228.58064516129, 
    3291.26666666667, 2055.93548387097, 2021.53333333333, 3950.92857142857, 
    1930.86666666667, 1284.92857142857, 631.766666666667, 1228.58064516129, 
    566.290322580645, 301.064516129032, 956.935483870968, 2055.93548387097, 
    2021.53333333333, 1228.58064516129, 3378.16666666667, 1930.86666666667, 
    1284.92857142857, 631.766666666667, 1201.45161290323, 403.354838709677, 
    3950.92857142857, 559.1, 725.967741935484, 301.064516129032, 
    2152.03448275862, 2643.22580645161, 3291.26666666667, 5504.83333333333, 
    927.161290322581, 6664.56666666667, 1228.58064516129, 559.1, 
    3378.16666666667, 1930.86666666667, 2055.93548387097, 631.6, 
    403.354838709677, 3950.92857142857, 2152.03448275862, 764.6, 
    6970.35483870968, 7787.61290322581, 2055.93548387097, 631.6, 
    282.870967741935, 1284.92857142857, 1201.45161290323, 3950.92857142857, 
    1228.58064516129, 559.1, 566.290322580645, 2643.22580645161, 
    764.6, 956.935483870968, 927.161290322581, 1395.51612903226, 
    1284.92857142857, 1201.45161290323, 1228.58064516129, 1170.67741935484, 
    2055.93548387097, 300.322580645161, 3950.92857142857, 1249.96774193548, 
    2152.03448275862, 6664.56666666667, 1228.58064516129, 282.870967741935, 
    2643.22580645161, 5518.5), Avg_Temperature = c(19.3966666666667, 
    20.6451612903226, 23.57, 21.1322580645161, 13.5448275862069, 
    19.1833333333333, 20.9741935483871, 19.0548387096774, 24.25, 
    16.2483870967742, 24.25, 17.8677419354839, 24.9533333333333, 
    14.24, 24.25, 22.65, 16.2483870967742, 21.1322580645161, 
    17.8677419354839, 24.0633333333333, 16.2483870967742, 24.25, 
    13.9785714285714, 14.2, 12.9357142857143, 18.71, 17.8677419354839, 
    20.6451612903226, 21.1967741935484, 20.9741935483871, 16.2483870967742, 
    24.25, 17.8677419354839, 22.65, 14.2, 12.9357142857143, 18.71, 
    26.1903225806452, 21.1322580645161, 13.9785714285714, 19.3966666666667, 
    25.041935483871, 21.1967741935484, 13.5448275862069, 16.3903225806452, 
    24.0633333333333, 22.24, 14.6387096774194, 21.96, 17.8677419354839, 
    19.3966666666667, 22.65, 14.2, 16.2483870967742, 24.148275862069, 
    21.1322580645161, 13.9785714285714, 13.5448275862069, 19.1833333333333, 
    24.0225806451613, 10.3903225806452, 16.2483870967742, 24.148275862069, 
    25.4161290322581, 12.9357142857143, 26.1903225806452, 13.9785714285714, 
    17.8677419354839, 19.3966666666667, 20.6451612903226, 16.3903225806452, 
    19.1833333333333, 20.9741935483871, 14.6387096774194, 18.2870967741935, 
    12.9357142857143, 26.1903225806452, 17.8677419354839, 18.3931034482759, 
    16.2483870967742, 21.5387096774194, 13.9785714285714, 9.87741935483871, 
    13.5448275862069, 21.96, 17.8677419354839, 25.4161290322581, 
    16.3903225806452, 22.7866666666667), Avg_Turbidity = c(8.70294117647059, 
    9.18064516129032, 14.923, 4.20741935483871, 13.2118518518519, 
    10.671, 9.1, 5.04903225806452, 7.917, 13.971935483871, 7.917, 
    7.1641935483871, 6.52310344827586, 6.97133333333333, 7.917, 
    21.7596666666667, 13.971935483871, 4.20741935483871, 7.1641935483871, 
    9.308, 13.971935483871, 7.917, 6.77928571428571, 9.01107142857143, 
    8.74107142857143, 9.863, 7.1641935483871, 9.18064516129032, 
    5.70387096774194, 9.1, 13.971935483871, 7.917, 7.1641935483871, 
    21.7596666666667, 9.01107142857143, 8.74107142857143, 9.863, 
    11.6293548387097, 4.20741935483871, 6.77928571428571, 8.70294117647059, 
    9.20033333333333, 5.70387096774194, 13.2118518518519, 12.4351612903226, 
    9.308, 7.12607142857143, 24.1138709677419, 24.168, 7.1641935483871, 
    8.70294117647059, 21.7596666666667, 9.01107142857143, 13.971935483871, 
    16.0827586206897, 4.20741935483871, 6.77928571428571, 13.2118518518519, 
    10.671, 9.17709677419355, 40.8825806451613, 13.971935483871, 
    16.0827586206897, 8.49, 8.74107142857143, 11.6293548387097, 
    6.77928571428571, 7.1641935483871, 8.70294117647059, 9.18064516129032, 
    12.4351612903226, 10.671, 9.1, 24.1138709677419, 6.96903225806452, 
    8.74107142857143, 11.6293548387097, 7.1641935483871, 8.83931034482759, 
    13.971935483871, 8.71935483870968, 6.77928571428571, 7.78612903225806, 
    13.2118518518519, 24.168, 7.1641935483871, 8.49, 12.4351612903226, 
    10.6056666666667), n_Salmonids = c(25, 3, 10, 0, 187, 46, 
    31, 0, 0, 120, 0, 56, 0, 0, 0, 0, 120, 0, 56, 1, 120, 0, 
    101, 0, 6, 324, 56, 3, 0, 31, 120, 0, 56, 0, 0, 6, 324, 0, 
    0, 101, 25, 0, 0, 187, 394, 1, 0, 227, 2354, 56, 25, 0, 0, 
    120, 1, 0, 101, 187, 46, 0, 1794, 120, 1, 0, 6, 0, 101, 56, 
    25, 3, 394, 46, 31, 227, 1, 6, 0, 56, 0, 120, 50, 101, 41, 
    187, 2354, 56, 0, 394, 0), ENTRY = c(1L, 1L, NA, NA, NA, 
    NA, NA, NA, NA, NA, NA, NA, NA, NA, 1L, NA, NA, NA, NA, NA, 
    1L, 1L, 1L, NA, NA, NA, NA, NA, NA, NA, 1L, 1L, 1L, NA, NA, 
    NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, 3L, 
    2L, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, 1L, 1L, 2L, NA, 
    NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, 1L, 1L, 2L, NA, NA, 
    NA, NA, NA, NA, NA, NA, NA, NA, NA), EXIT = c(1L, 1L, 2L, 
    1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 1L, 1L, 2L, 1L, 1L, 1L, 
    1L, 1L, 1L, 1L, 5L, 1L, 1L, 1L, 3L, 1L, 2L, 1L, 1L, 1L, 3L, 
    1L, 1L, 1L, 3L, 1L, 2L, 1L, 1L, 1L, 4L, 1L, 2L, 1L, 1L, 1L, 
    1L, 3L, 1L, 1L, 1L, 3L, 1L, 2L, 3L, 2L, 1L, 1L, 1L, 1L, 1L, 
    1L, 4L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 3L, 1L, 5L, 
    1L, 2L, 1L, 2L, 1L, 2L, 1L, 1L, 1L, 1L, 1L), n_transit = c(3L, 
    4L, 2L, 1L, 1L, 3L, 2L, 1L, 1L, 1L, 2L, 1L, 1L, 1L, 3L, 2L, 
    2L, 1L, 2L, 1L, 7L, 2L, 8L, 1L, 3L, 2L, 5L, 1L, 2L, 1L, 8L, 
    2L, 4L, 1L, 2L, 1L, 3L, 1L, 3L, 3L, 1L, 1L, 5L, 2L, 2L, 2L, 
    1L, 1L, 1L, 8L, 3L, 2L, 1L, 5L, 1L, 3L, 5L, 6L, 3L, 1L, 1L, 
    3L, 2L, 3L, 5L, 1L, 2L, 3L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 5L, 
    2L, 9L, 1L, 4L, 1L, 2L, 1L, 4L, 1L, 1L, 1L, 1L, 1L)), class = c("tbl_df", 
"tbl", "data.frame"), row.names = c(NA, -89L))

, пытающийся запустить эту модель, используя пакет 'gam': 

scope_list = list(
  "EstimatedAge" = ~1 + EstimatedAge + logistic(EstimatedAge) + s(EstimatedAge),
  "month"=  ~1 + month + Poly(month, 2) + Poly(month, 3) + s(month),
  "at_large"= ~1 + at_large + s(at_large) + Poly(at_large, 2),
  "Avg_Flow"= ~1 + Avg_Flow + s(Avg_Flow) + Poly(Avg_Flow, df = 2),
  "Avg_Temperature"= ~1 + Avg_Temperature + s(Avg_Temperature) + Poly( Avg_Temperature, 2) + Poly(Avg_Temperature, 3),
  "Avg_Turbidity"= ~1 + Avg_Turbidity + s(Avg_Turbidity) + Poly(Avg_Turbidity, 2) + Poly(Avg_Turbidity, 3),
  "n_Salmonids"= ~1 + n_Salmonids + s(n_Salmonids) + Poly(n_Salmonids,2) + Poly(n_Salmonids,3))

#build a model of Exit transits
start_model_basic = gam(EXIT ~ month, data = monthly_summary[monthly_summary$Species == "Striped Bass" & monthly_summary$EXIT > 0,])

step.Gam(start_model_basic, scope = scope_list)

, который выдает эту ошибку: 

Error in model.frame.default(formula = EXIT ~ month + s(at_large), data = monthly_summary[monthly_summary$Species ==  : 
  invalid type (list) for variable 's(at_large)'

Но быстрая проверка str () показывает: 

Classes ‘tbl_df’, ‘tbl’ and 'data.frame':   650 obs. of  12 variables:
 $ year           : int  2013 2015 2015 2016 2013 2014 2016 2016 2016 2013 ...
 $ month          : int  8 4 5 7 6 10 2 4 5 5 ...
 $ EstimatedAge   : num  -1 -1 -1 -1 -1 -1 -1 -1 -1 -1 ...
 $ Species        : Factor w/ 3 levels "Catfish","Largemouth Bass",..: 1 1 1 1 1 1 1 1 1 1 ...
 $ at_large       : int  6 8 13 10 6 3 14 16 13 0 ...
 $ Avg_Flow       : num  5821 559 566 5922 2048 ...
 $ Avg_Temperature: num  24.1 19.4 20.6 24.9 23.6 ...
 $ Avg_Turbidity  : num  14.46 8.7 9.18 14.01 14.92 ...
 $ n_Salmonids    : num  0 25 3 0 10 ...
 $ ENTRY          : int  1 1 1 1 NA NA NA NA NA NA ...
 $ EXIT           : int  NA 1 1 NA 2 1 1 1 1 NA ...
 $ n_transit      : int  1 3 4 1 2 1 1 3 2 0 ...

Итак, если at_large имеет тип "int", почему он видит его как список? Похоже, одна и та же ошибка возникает для всех переменных, если я постепенно удаляю каждую ошибочную переменную.

...