FinalFinal1
Maliat I
12/6/2021
R Markdown
R Markdown
Overview
There are millions of stray pets around the world, some of which are fortunate enough to be adopted while many others are not. While adoption of a pet is often the definition of success, the rate at which a pet is adopted is also a key success factor - pets that take a long time to adopt contribute to over-crowded animal shelters and can prevent taking on new strays. Sadly, pets that are not adopted eventually need to be euthanized.
Learn more about the data
What to Predict
Predictor (Adoption Speed) Description: Predict how quickly, if at all, a pet is adopted.
The values are determined in the following way: 0 - Pet was adopted on the same day as it was listed. 1 - Pet was adopted between 1 and 7 days (1st week) after being listed. 2 - Pet was adopted between 8 and 30 days (1st month) after being listed. 3 - Pet was adopted between 31 and 90 days (2nd & 3rd month) after being listed. 4 - No adoption after 100 days of being listed.
This Notebook…
The data has no missing values, but there are a number of features in text that need to be converted to some numeric value. This notebook performs those changes.
knitr::opts_chunk$set(echo = TRUE)
knitr::opts_chunk$set(message = FALSE)
knitr::opts_chunk$set(warning = FALSE)library(dplyr)
library(reshape)
library(ggplot2)
library(purrr)
library(psych)
library(tidyr)library(scales)Load Data
Load the data
## Type Name Age Breed1 Breed2 Gender Color1 Color2 Color3
## 1 1 Lil Milo 2 0 26 2 2 0 0
## 2 1 Bella 4 Months Puppy! 4 0 307 2 2 3 0
## MaturitySize FurLength Vaccinated Dewormed Sterilized Health Quantity Fee
## 1 2 1 1 1 2 1 1 0
## 2 2 1 1 1 2 1 1 100
## State RescuerID VideoAmt
## 1 41326 1a2113010d6048d5410b265347b35c91 0
## 2 41326 3673e167fc9932b13149bed1f2a0180a 0
## Description
## 1 Milo went missing after a week with her new adoptive family. Only 3 months old, light brown coat. Missing from Jalan Kiara, Bandar Botanic, Klang. Please call Su at if you've seen her.
## 2 She's only 4 months old, very friendly and loving. Loves attention. A little naughty sometimes. But she's adorable. I adopted her from MDDB, but recently I have just moved to a condo. Im finding a perfect and loving home for her.
## PetID PhotoAmt AdoptionSpeed
## 1 375905770 3 3
## 2 da8d4a273 5 4Missing Values Count
There are no missing values
map(data, ~sum(is.na(.))) %>% t()## Type Name Age Breed1 Breed2 Gender Color1 Color2 Color3 MaturitySize
## [1,] 0 0 0 0 0 0 0 0 0 0
## FurLength Vaccinated Dewormed Sterilized Health Quantity Fee State
## [1,] 0 0 0 0 0 0 0 0
## RescuerID VideoAmt Description PetID PhotoAmt AdoptionSpeed
## [1,] 0 0 0 0 0 0Show the type of each data
str(data)## 'data.frame': 14993 obs. of 24 variables:
## $ Type : int 1 1 2 1 1 1 1 1 1 1 ...
## $ Name : chr "Lil Milo" "Bella 4 Months Puppy!" "" "\"Boy Boy\"" ...
## $ Age : int 2 4 3 72 2 5 24 3 0 24 ...
## $ Breed1 : int 0 0 0 0 0 1 1 3 5 5 ...
## $ Breed2 : int 26 307 266 307 205 0 0 0 0 307 ...
## $ Gender : int 2 2 3 1 2 2 3 1 2 2 ...
## $ Color1 : int 2 2 1 1 2 1 4 2 1 3 ...
## $ Color2 : int 0 3 4 2 5 4 0 0 2 5 ...
## $ Color3 : int 0 0 7 0 7 7 0 0 0 0 ...
## $ MaturitySize : int 2 2 1 2 1 2 2 2 1 2 ...
## $ FurLength : int 1 1 1 2 1 1 1 2 1 2 ...
## $ Vaccinated : int 1 1 2 2 2 2 1 2 2 1 ...
## $ Dewormed : int 1 1 1 2 2 2 1 1 2 1 ...
## $ Sterilized : int 2 2 2 2 2 2 1 2 2 1 ...
## $ Health : int 1 1 1 1 1 1 1 1 2 1 ...
## $ Quantity : int 1 1 3 1 1 2 2 4 1 1 ...
## $ Fee : int 0 100 0 0 1 0 0 0 0 0 ...
## $ State : int 41326 41326 41401 41326 41336 41326 41330 41326 41401 41326 ...
## $ RescuerID : chr "1a2113010d6048d5410b265347b35c91" "3673e167fc9932b13149bed1f2a0180a" "f7cff59d10c867bdee12c3f35f34d086" "94b991f8dc1e0bb903ca8d4d492c8d43" ...
## $ VideoAmt : int 0 0 0 0 0 0 0 0 0 0 ...
## $ Description : chr "Milo went missing after a week with her new adoptive family. Only 3 months old, light brown coat. Missing from "| __truncated__ "She's only 4 months old, very friendly and loving. Loves attention. A little naughty sometimes. But she's adora"| __truncated__ "Mama cat came to house and gave birth to these 03 lovely kittens, please adopt them and give them a home sweet home." "He is a stray dog found wandering around University Putra Malaysia (UPM), Serdang main campus. I have been told"| __truncated__ ...
## $ PetID : chr "375905770" "da8d4a273" "27e74e45c" "7b5bee232" ...
## $ PhotoAmt : int 3 5 11 5 0 2 5 3 2 2 ...
## $ AdoptionSpeed: int 3 4 2 4 3 4 4 4 1 4 ...Adoption rate
It can be observed that the rate of not getting adopted after 100 days of being listed is more frequent.
data %>%
ggplot(aes(x= AdoptionSpeed, fill = AdoptionSpeed)) +
geom_bar(stat = "count", color = "black") +
theme_minimal() +
theme(axis.title.y = element_blank()) +
scale_y_continuous(labels = comma) +
scale_fill_brewer(palette="blue") +
theme(legend.position = "top") 
### Exploration
library(tidyverse)
library(jsonlite)
library(scales)
library(lubridate)
library(repr)
library(ggrepel)
library(gridExtra)
library(tidytext)
library(grid)
library(rjson)
library(xgboost)
library(caret)
library(Metrics)
library(Ckmeans.1d.dp)library(dplyr)
train <- read_csv("https://raw.githubusercontent.com/akarimhammoud/Data_621/main/Final%20Project/data/TrainingData/train.csv")
test <- read_csv("https://raw.githubusercontent.com/akarimhammoud/Data_621/main/Final%20Project/data/TestData/test.csv")
state_labels <- read_csv("https://raw.githubusercontent.com/akarimhammoud/Data_621/main/Final%20Project/data/state_labels.csv")
breed_labels <- read_csv("https://raw.githubusercontent.com/akarimhammoud/Data_621/main/Final%20Project/data/TrainingData/breed_labels.csv")
color_labels <- read_csv("https://raw.githubusercontent.com/akarimhammoud/Data_621/main/Final%20Project/data/color_labels.csv")
tr_te <- bind_rows(train, test)
train <- left_join(train, breed_labels %>%dplyr:: select(Breed1=BreedID, MainBreed=BreedName), by="Breed1")
train <- left_join(train, breed_labels %>%dplyr:: select(Breed2=BreedID, SecondBreed=BreedName), by="Breed2")
train <- left_join(train, color_labels %>%dplyr:: select(Color1=ColorID, ColorName1=ColorName), by="Color1")
train <- left_join(train, color_labels %>% dplyr::select(Color2=ColorID, ColorName2=ColorName), by="Color2")
train <- left_join(train, color_labels %>% dplyr::select(Color3=ColorID, ColorName3=ColorName), by="Color3")
train <- train %>% dplyr::select(-State, -Breed1, -Breed2, - Color1, -Color2, -Color3)
train <- train %>% mutate_at(vars(Type, Gender, AdoptionSpeed), as.factor)
train <- train %>% mutate(Type=recode(Type, "1"= "Dog", "2"= "Cat"),
Gender=recode(Gender, "1"= "Male", "2" = "Female", "3"= "Mixed"),
AdoptionSpeed=recode(AdoptionSpeed,
"0"= "0 - Adopted on the same day",
"1" = "1 - Adopted between 1 and 7 days",
"2" = "2 - Adopted between 8 and 30 days",
"3" = "3 - Adopted between 31 and 90 days",
"4" = "4 - No adoption after 100 days"))
train <- train %>% mutate_if(is_character, as_factor)
glimpse(train)## Rows: 14,993
## Columns: 23
## $ Type <fct> Dog, Dog, Cat, Dog, Dog, Dog, Dog, Dog, Dog, Dog, Dog, D~
## $ Name <fct> "Lil Milo", "Bella 4 Months Puppy!", NA, "\"Boy Boy\"", ~
## $ Age <dbl> 2, 4, 3, 72, 2, 5, 24, 3, 0, 24, 14, 60, 84, 21, 1, 1, 1~
## $ Gender <fct> Female, Female, Mixed, Male, Female, Female, Mixed, Male~
## $ MaturitySize <dbl> 2, 2, 1, 2, 1, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,~
## $ FurLength <dbl> 1, 1, 1, 2, 1, 1, 1, 2, 1, 2, 1, 1, 1, 1, 3, 2, 1, 2, 3,~
## $ Vaccinated <dbl> 1, 1, 2, 2, 2, 2, 1, 2, 2, 1, 1, 1, 1, 1, 2, 2, 2, 1, 1,~
## $ Dewormed <dbl> 1, 1, 1, 2, 2, 2, 1, 1, 2, 1, 1, 1, 1, 1, 2, 2, 2, 3, 1,~
## $ Sterilized <dbl> 2, 2, 2, 2, 2, 2, 1, 2, 2, 1, 3, 1, 2, 1, 2, 2, 2, 3, 1,~
## $ Health <dbl> 1, 1, 1, 1, 1, 1, 1, 1, 2, 1, 1, 1, 1, 2, 1, 1, 1, 1, 1,~
## $ Quantity <dbl> 1, 1, 3, 1, 1, 2, 2, 4, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,~
## $ Fee <dbl> 0, 100, 0, 0, 1, 0, 0, 0, 0, 0, 500, 0, 0, 0, 0, 0, 0, 0~
## $ RescuerID <fct> 1a2113010d6048d5410b265347b35c91, 3673e167fc9932b13149be~
## $ VideoAmt <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,~
## $ Description <fct> "Milo went missing after a week with her new adoptive fa~
## $ PetID <fct> 375905770, da8d4a273, 27e74e45c, 7b5bee232, 0327b8e94, f~
## $ PhotoAmt <dbl> 3, 5, 11, 5, 0, 2, 5, 3, 2, 2, 2, 2, 1, 2, 4, 4, 3, 1, 3~
## $ AdoptionSpeed <fct> 3 - Adopted between 31 and 90 days, 4 - No adoption afte~
## $ MainBreed <fct> NA, NA, NA, NA, NA, Affenpinscher, Affenpinscher, Aireda~
## $ SecondBreed <fct> Belgian Shepherd Malinois, Mixed Breed, Dom Short Hair, ~
## $ ColorName1 <fct> Brown, Brown, Black, Black, Brown, Black, Yellow, Brown,~
## $ ColorName2 <fct> NA, Golden, Yellow, Brown, Cream, Yellow, NA, NA, Brown,~
## $ ColorName3 <fct> NA, NA, White, NA, White, White, NA, NA, NA, NA, NA, NA,~Pure Breed Feature:
We will observe if pure breed pets are getting adopted faster than the pets that are not pure breed.
not_pure <- c("Domestic Short Hair", "Domestic Medium Hair", "Domestic Long Hair", "Mixed Breed")
train$pure_breed <- ifelse(train$MainBreed %in% not_pure, 0, 1)
train %>% filter(pure_breed==1) %>% count(Type, MainBreed) %>% group_by(Type) %>% top_n(10, n) %>%
ggplot(aes(x=reorder(MainBreed, -n), y=n))+
geom_bar(stat="identity", fill="blue") +
facet_wrap(~Type, scales = "free_x") +
theme(axis.text.x = element_text(angle = 45, hjust = 1)) +
labs(x="Most common pure breeds", y="number of pets")
train %>% count(AdoptionSpeed, pure_breed) %>%
ggplot(aes(x=AdoptionSpeed, y=n, fill=as.factor(pure_breed))) +
geom_bar(stat="identity", position="fill") +
theme(axis.text.x = element_text(angle = 45, hjust = 1)) +
guides(fill=guide_legend(title="Pure Breed")) +
scale_y_continuous(labels=percent) +
labs(x="", y="percent")
### As pure breed pets have faster adoption rate, a new variable is created to identify pure breed pets.
tr_te <- left_join(tr_te, state_labels %>% dplyr::rename(State=StateID), by="State")
tr_te <- left_join(tr_te, breed_labels %>% dplyr::select(Breed1=BreedID, MainBreed=BreedName), by="Breed1")
#creating Has Name variable
tr_te$has_name <- ifelse(is.na(tr_te$Name), 0, 1)
#creating Pure Breed variable
not_pure <- c("Domestic Short Hair", "Domestic Medium Hair", "Domestic Long Hair", "Mixed Breed")
tr_te$pure_breed <- ifelse(tr_te$MainBreed %in% not_pure, 0, 1)
#making Not Specified in ordinal factors NA (just in case there are any in stage 2)
tr_te$MaturitySize[tr_te$MaturitySize==0] <- NA
tr_te$FurLength[tr_te$FurLength==0] <- NA
tr_te$Health[tr_te$Health==0] <- NA
categorical_vars <- c("Type", "Gender", "Vaccinated", "Dewormed", "Sterilized", "StateName", "MainBreed", "has_name", "pure_breed", "Breed2", "Color1", "Color2", "Color3")
tr_te <- tr_te %>% dplyr::select(-Name, -Breed1, -RescuerID, -Description, -State, -PetID) %>%
mutate_at(categorical_vars, funs(factor(.))) %>% mutate_if(is.numeric, as.integer)
glimpse(tr_te)## Rows: 18,941
## Columns: 22
## $ Type <fct> 1, 1, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,~
## $ Age <int> 2, 4, 3, 72, 2, 5, 24, 3, 0, 24, 14, 60, 84, 21, 1, 1, 1~
## $ Breed2 <fct> 26, 307, 266, 307, 205, 0, 0, 0, 0, 307, 0, 0, 0, 307, 0~
## $ Gender <fct> 2, 2, 3, 1, 2, 2, 3, 1, 2, 2, 1, 2, 1, 2, 2, 2, 2, 2, 1,~
## $ Color1 <fct> 2, 2, 1, 1, 2, 1, 4, 2, 1, 3, 2, 1, 2, 2, 7, 2, 2, 1, 1,~
## $ Color2 <fct> 0, 3, 4, 2, 5, 4, 0, 0, 2, 5, 0, 7, 0, 7, 0, 0, 6, 2, 2,~
## $ Color3 <fct> 0, 0, 7, 0, 7, 7, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 7, 0, 0,~
## $ MaturitySize <int> 2, 2, 1, 2, 1, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,~
## $ FurLength <int> 1, 1, 1, 2, 1, 1, 1, 2, 1, 2, 1, 1, 1, 1, 3, 2, 1, 2, 3,~
## $ Vaccinated <fct> 1, 1, 2, 2, 2, 2, 1, 2, 2, 1, 1, 1, 1, 1, 2, 2, 2, 1, 1,~
## $ Dewormed <fct> 1, 1, 1, 2, 2, 2, 1, 1, 2, 1, 1, 1, 1, 1, 2, 2, 2, 3, 1,~
## $ Sterilized <fct> 2, 2, 2, 2, 2, 2, 1, 2, 2, 1, 3, 1, 2, 1, 2, 2, 2, 3, 1,~
## $ Health <int> 1, 1, 1, 1, 1, 1, 1, 1, 2, 1, 1, 1, 1, 2, 1, 1, 1, 1, 1,~
## $ Quantity <int> 1, 1, 3, 1, 1, 2, 2, 4, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,~
## $ Fee <int> 0, 100, 0, 0, 1, 0, 0, 0, 0, 0, 500, 0, 0, 0, 0, 0, 0, 0~
## $ VideoAmt <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,~
## $ PhotoAmt <int> 3, 5, 11, 5, 0, 2, 5, 3, 2, 2, 2, 2, 1, 2, 4, 4, 3, 1, 3~
## $ AdoptionSpeed <int> 3, 4, 2, 4, 3, 4, 4, 4, 1, 4, 4, 3, 3, 3, 4, 4, 1, 4, 4,~
## $ StateName <fct> Selangor, Selangor, Kuala Lumpur, Selangor, Johor, Selan~
## $ MainBreed <fct> NA, NA, NA, NA, NA, Affenpinscher, Affenpinscher, Aireda~
## $ has_name <fct> 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1,~
## $ pure_breed <fct> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,~glimpse(train)## Rows: 14,993
## Columns: 24
## $ Type <fct> Dog, Dog, Cat, Dog, Dog, Dog, Dog, Dog, Dog, Dog, Dog, D~
## $ Name <fct> "Lil Milo", "Bella 4 Months Puppy!", NA, "\"Boy Boy\"", ~
## $ Age <dbl> 2, 4, 3, 72, 2, 5, 24, 3, 0, 24, 14, 60, 84, 21, 1, 1, 1~
## $ Gender <fct> Female, Female, Mixed, Male, Female, Female, Mixed, Male~
## $ MaturitySize <dbl> 2, 2, 1, 2, 1, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,~
## $ FurLength <dbl> 1, 1, 1, 2, 1, 1, 1, 2, 1, 2, 1, 1, 1, 1, 3, 2, 1, 2, 3,~
## $ Vaccinated <dbl> 1, 1, 2, 2, 2, 2, 1, 2, 2, 1, 1, 1, 1, 1, 2, 2, 2, 1, 1,~
## $ Dewormed <dbl> 1, 1, 1, 2, 2, 2, 1, 1, 2, 1, 1, 1, 1, 1, 2, 2, 2, 3, 1,~
## $ Sterilized <dbl> 2, 2, 2, 2, 2, 2, 1, 2, 2, 1, 3, 1, 2, 1, 2, 2, 2, 3, 1,~
## $ Health <dbl> 1, 1, 1, 1, 1, 1, 1, 1, 2, 1, 1, 1, 1, 2, 1, 1, 1, 1, 1,~
## $ Quantity <dbl> 1, 1, 3, 1, 1, 2, 2, 4, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,~
## $ Fee <dbl> 0, 100, 0, 0, 1, 0, 0, 0, 0, 0, 500, 0, 0, 0, 0, 0, 0, 0~
## $ RescuerID <fct> 1a2113010d6048d5410b265347b35c91, 3673e167fc9932b13149be~
## $ VideoAmt <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,~
## $ Description <fct> "Milo went missing after a week with her new adoptive fa~
## $ PetID <fct> 375905770, da8d4a273, 27e74e45c, 7b5bee232, 0327b8e94, f~
## $ PhotoAmt <dbl> 3, 5, 11, 5, 0, 2, 5, 3, 2, 2, 2, 2, 1, 2, 4, 4, 3, 1, 3~
## $ AdoptionSpeed <fct> 3 - Adopted between 31 and 90 days, 4 - No adoption afte~
## $ MainBreed <fct> NA, NA, NA, NA, NA, Affenpinscher, Affenpinscher, Aireda~
## $ SecondBreed <fct> Belgian Shepherd Malinois, Mixed Breed, Dom Short Hair, ~
## $ ColorName1 <fct> Brown, Brown, Black, Black, Brown, Black, Yellow, Brown,~
## $ ColorName2 <fct> NA, Golden, Yellow, Brown, Cream, Yellow, NA, NA, Brown,~
## $ ColorName3 <fct> NA, NA, White, NA, White, White, NA, NA, NA, NA, NA, NA,~
## $ pure_breed <dbl> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,~glimpse(tr_te)## Rows: 18,941
## Columns: 22
## $ Type <fct> 1, 1, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,~
## $ Age <int> 2, 4, 3, 72, 2, 5, 24, 3, 0, 24, 14, 60, 84, 21, 1, 1, 1~
## $ Breed2 <fct> 26, 307, 266, 307, 205, 0, 0, 0, 0, 307, 0, 0, 0, 307, 0~
## $ Gender <fct> 2, 2, 3, 1, 2, 2, 3, 1, 2, 2, 1, 2, 1, 2, 2, 2, 2, 2, 1,~
## $ Color1 <fct> 2, 2, 1, 1, 2, 1, 4, 2, 1, 3, 2, 1, 2, 2, 7, 2, 2, 1, 1,~
## $ Color2 <fct> 0, 3, 4, 2, 5, 4, 0, 0, 2, 5, 0, 7, 0, 7, 0, 0, 6, 2, 2,~
## $ Color3 <fct> 0, 0, 7, 0, 7, 7, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 7, 0, 0,~
## $ MaturitySize <int> 2, 2, 1, 2, 1, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,~
## $ FurLength <int> 1, 1, 1, 2, 1, 1, 1, 2, 1, 2, 1, 1, 1, 1, 3, 2, 1, 2, 3,~
## $ Vaccinated <fct> 1, 1, 2, 2, 2, 2, 1, 2, 2, 1, 1, 1, 1, 1, 2, 2, 2, 1, 1,~
## $ Dewormed <fct> 1, 1, 1, 2, 2, 2, 1, 1, 2, 1, 1, 1, 1, 1, 2, 2, 2, 3, 1,~
## $ Sterilized <fct> 2, 2, 2, 2, 2, 2, 1, 2, 2, 1, 3, 1, 2, 1, 2, 2, 2, 3, 1,~
## $ Health <int> 1, 1, 1, 1, 1, 1, 1, 1, 2, 1, 1, 1, 1, 2, 1, 1, 1, 1, 1,~
## $ Quantity <int> 1, 1, 3, 1, 1, 2, 2, 4, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,~
## $ Fee <int> 0, 100, 0, 0, 1, 0, 0, 0, 0, 0, 500, 0, 0, 0, 0, 0, 0, 0~
## $ VideoAmt <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,~
## $ PhotoAmt <int> 3, 5, 11, 5, 0, 2, 5, 3, 2, 2, 2, 2, 1, 2, 4, 4, 3, 1, 3~
## $ AdoptionSpeed <int> 3, 4, 2, 4, 3, 4, 4, 4, 1, 4, 4, 3, 3, 3, 4, 4, 1, 4, 4,~
## $ StateName <fct> Selangor, Selangor, Kuala Lumpur, Selangor, Johor, Selan~
## $ MainBreed <fct> NA, NA, NA, NA, NA, Affenpinscher, Affenpinscher, Aireda~
## $ has_name <fct> 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1,~
## $ pure_breed <fct> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,~Fast adoption:
Adoption speed less than 3 is categorized as high(1) and more than 3 is categorized as low(0).
High = ifelse(tr_te$AdoptionSpeed<3, "1", "0")
tr_te = data.frame(tr_te, High)glimpse(tr_te)## Rows: 18,941
## Columns: 23
## $ Type <fct> 1, 1, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,~
## $ Age <int> 2, 4, 3, 72, 2, 5, 24, 3, 0, 24, 14, 60, 84, 21, 1, 1, 1~
## $ Breed2 <fct> 26, 307, 266, 307, 205, 0, 0, 0, 0, 307, 0, 0, 0, 307, 0~
## $ Gender <fct> 2, 2, 3, 1, 2, 2, 3, 1, 2, 2, 1, 2, 1, 2, 2, 2, 2, 2, 1,~
## $ Color1 <fct> 2, 2, 1, 1, 2, 1, 4, 2, 1, 3, 2, 1, 2, 2, 7, 2, 2, 1, 1,~
## $ Color2 <fct> 0, 3, 4, 2, 5, 4, 0, 0, 2, 5, 0, 7, 0, 7, 0, 0, 6, 2, 2,~
## $ Color3 <fct> 0, 0, 7, 0, 7, 7, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 7, 0, 0,~
## $ MaturitySize <int> 2, 2, 1, 2, 1, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,~
## $ FurLength <int> 1, 1, 1, 2, 1, 1, 1, 2, 1, 2, 1, 1, 1, 1, 3, 2, 1, 2, 3,~
## $ Vaccinated <fct> 1, 1, 2, 2, 2, 2, 1, 2, 2, 1, 1, 1, 1, 1, 2, 2, 2, 1, 1,~
## $ Dewormed <fct> 1, 1, 1, 2, 2, 2, 1, 1, 2, 1, 1, 1, 1, 1, 2, 2, 2, 3, 1,~
## $ Sterilized <fct> 2, 2, 2, 2, 2, 2, 1, 2, 2, 1, 3, 1, 2, 1, 2, 2, 2, 3, 1,~
## $ Health <int> 1, 1, 1, 1, 1, 1, 1, 1, 2, 1, 1, 1, 1, 2, 1, 1, 1, 1, 1,~
## $ Quantity <int> 1, 1, 3, 1, 1, 2, 2, 4, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,~
## $ Fee <int> 0, 100, 0, 0, 1, 0, 0, 0, 0, 0, 500, 0, 0, 0, 0, 0, 0, 0~
## $ VideoAmt <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,~
## $ PhotoAmt <int> 3, 5, 11, 5, 0, 2, 5, 3, 2, 2, 2, 2, 1, 2, 4, 4, 3, 1, 3~
## $ AdoptionSpeed <int> 3, 4, 2, 4, 3, 4, 4, 4, 1, 4, 4, 3, 3, 3, 4, 4, 1, 4, 4,~
## $ StateName <fct> Selangor, Selangor, Kuala Lumpur, Selangor, Johor, Selan~
## $ MainBreed <fct> NA, NA, NA, NA, NA, Affenpinscher, Affenpinscher, Aireda~
## $ has_name <fct> 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1,~
## $ pure_breed <fct> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,~
## $ High <chr> "0", "0", "1", "0", "0", "0", "0", "0", "1", "0", "0", "~tr_te$High<-as.numeric(tr_te$High)glimpse(tr_te)## Rows: 18,941
## Columns: 23
## $ Type <fct> 1, 1, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,~
## $ Age <int> 2, 4, 3, 72, 2, 5, 24, 3, 0, 24, 14, 60, 84, 21, 1, 1, 1~
## $ Breed2 <fct> 26, 307, 266, 307, 205, 0, 0, 0, 0, 307, 0, 0, 0, 307, 0~
## $ Gender <fct> 2, 2, 3, 1, 2, 2, 3, 1, 2, 2, 1, 2, 1, 2, 2, 2, 2, 2, 1,~
## $ Color1 <fct> 2, 2, 1, 1, 2, 1, 4, 2, 1, 3, 2, 1, 2, 2, 7, 2, 2, 1, 1,~
## $ Color2 <fct> 0, 3, 4, 2, 5, 4, 0, 0, 2, 5, 0, 7, 0, 7, 0, 0, 6, 2, 2,~
## $ Color3 <fct> 0, 0, 7, 0, 7, 7, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 7, 0, 0,~
## $ MaturitySize <int> 2, 2, 1, 2, 1, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,~
## $ FurLength <int> 1, 1, 1, 2, 1, 1, 1, 2, 1, 2, 1, 1, 1, 1, 3, 2, 1, 2, 3,~
## $ Vaccinated <fct> 1, 1, 2, 2, 2, 2, 1, 2, 2, 1, 1, 1, 1, 1, 2, 2, 2, 1, 1,~
## $ Dewormed <fct> 1, 1, 1, 2, 2, 2, 1, 1, 2, 1, 1, 1, 1, 1, 2, 2, 2, 3, 1,~
## $ Sterilized <fct> 2, 2, 2, 2, 2, 2, 1, 2, 2, 1, 3, 1, 2, 1, 2, 2, 2, 3, 1,~
## $ Health <int> 1, 1, 1, 1, 1, 1, 1, 1, 2, 1, 1, 1, 1, 2, 1, 1, 1, 1, 1,~
## $ Quantity <int> 1, 1, 3, 1, 1, 2, 2, 4, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,~
## $ Fee <int> 0, 100, 0, 0, 1, 0, 0, 0, 0, 0, 500, 0, 0, 0, 0, 0, 0, 0~
## $ VideoAmt <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,~
## $ PhotoAmt <int> 3, 5, 11, 5, 0, 2, 5, 3, 2, 2, 2, 2, 1, 2, 4, 4, 3, 1, 3~
## $ AdoptionSpeed <int> 3, 4, 2, 4, 3, 4, 4, 4, 1, 4, 4, 3, 3, 3, 4, 4, 1, 4, 4,~
## $ StateName <fct> Selangor, Selangor, Kuala Lumpur, Selangor, Johor, Selan~
## $ MainBreed <fct> NA, NA, NA, NA, NA, Affenpinscher, Affenpinscher, Aireda~
## $ has_name <fct> 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1,~
## $ pure_breed <fct> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,~
## $ High <dbl> 0, 0, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0,~library(MASS)
modelnegb <- glm.nb(High ~ ., data = tr_te)Negative Binomial Model:
summary(modelnegb)##
## Call:
## glm.nb(formula = High ~ ., data = tr_te, init.theta = 23950.02709,
## link = log)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -1.4076 -0.4663 -0.3909 0.5029 1.1392
##
## Coefficients: (3 not defined because of singularities)
## Estimate Std. Error
## (Intercept) 1.630e+00 7.223e-01
## Type2 -7.824e-01 6.447e-01
## Age -4.571e-04 9.434e-04
## Breed21 5.644e-01 1.001e+00
## Breed22 -2.885e-01 1.008e+00
## Breed24 -1.951e-01 1.029e+00
## Breed25 -1.051e-01 7.890e-01
## Breed210 4.339e-01 1.021e+00
## Breed214 -3.511e+01 4.745e+07
## Breed216 2.495e-01 7.414e-01
## Breed217 -3.466e+01 6.711e+07
## Breed218 1.539e-01 1.004e+00
## Breed219 5.096e-01 1.019e+00
## Breed220 7.630e-02 3.000e-01
## Breed221 -3.508e+01 4.745e+07
## Breed224 -4.349e-01 5.807e-01
## Breed225 3.302e+01 4.263e+07
## Breed226 4.186e-01 2.705e-01
## Breed236 -3.549e+01 6.711e+07
## Breed239 2.013e-01 4.491e-01
## Breed240 -3.550e+01 6.711e+07
## Breed244 2.565e-01 6.138e-01
## Breed249 2.886e-01 1.001e+00
## Breed250 3.766e-01 7.244e-01
## Breed258 -3.472e+01 6.711e+07
## Breed260 -1.083e-01 5.164e-01
## Breed265 1.113e-01 1.229e+00
## Breed269 4.511e-02 5.407e-01
## Breed270 5.456e-02 5.827e-01
## Breed272 1.177e-02 5.914e-01
## Breed275 5.651e-02 3.374e-01
## Breed276 -3.827e-01 4.227e-01
## Breed278 6.510e-02 3.804e-01
## Breed283 7.468e-01 1.026e+00
## Breed296 7.305e-01 1.039e+00
## Breed298 5.644e-01 6.018e-01
## Breed2102 3.965e-01 1.001e+00
## Breed2103 9.437e-02 1.691e-01
## Breed2104 -3.474e+01 6.711e+07
## Breed2109 -3.024e-01 2.422e-01
## Breed2111 -3.458e+01 6.711e+07
## Breed2115 -6.726e-03 1.016e+00
## Breed2117 -7.667e-01 1.001e+00
## Breed2119 1.757e-01 3.099e-01
## Breed2122 -3.523e+01 6.711e+07
## Breed2128 1.254e-01 3.366e-01
## Breed2129 7.650e-02 7.192e-01
## Breed2130 -1.071e-01 1.009e+00
## Breed2141 -1.478e-01 1.556e-01
## Breed2146 -3.605e+01 6.711e+07
## Breed2147 2.527e-01 5.124e-01
## Breed2150 4.935e-01 1.006e+00
## Breed2152 -2.656e-01 5.061e-01
## Breed2155 -4.815e-02 9.177e-01
## Breed2159 -3.557e+01 6.711e+07
## Breed2167 -3.554e+01 6.711e+07
## Breed2169 -1.290e-01 5.059e-01
## Breed2173 -4.240e-02 1.001e+00
## Breed2176 -3.485e+01 6.711e+07
## Breed2178 2.111e-01 7.143e-01
## Breed2179 3.313e-02 2.056e-01
## Breed2182 -3.572e+01 6.711e+07
## Breed2187 4.240e-03 4.544e-01
## Breed2188 -1.557e-01 1.043e+00
## Breed2189 -3.351e-02 1.797e-01
## Breed2190 -3.465e+01 6.711e+07
## Breed2192 -4.285e-01 1.013e+00
## Breed2195 -2.474e-01 2.671e-01
## Breed2200 1.512e-01 5.800e-01
## Breed2201 -4.351e-01 7.237e-01
## Breed2202 -1.360e-01 1.008e+00
## Breed2203 6.031e-01 1.001e+00
## Breed2204 -3.534e+01 6.711e+07
## Breed2205 -4.639e-02 2.293e-01
## Breed2206 -4.003e-01 5.901e-01
## Breed2207 5.764e-02 5.928e-01
## Breed2210 5.757e-01 1.006e+00
## Breed2212 2.275e-01 7.148e-01
## Breed2213 2.201e-01 2.125e-01
## Breed2218 -8.651e-02 1.555e-01
## Breed2227 2.641e-01 1.006e+00
## Breed2228 7.068e-01 7.212e-01
## Breed2237 8.388e-01 1.009e+00
## Breed2239 -2.581e-02 1.004e+00
## Breed2240 -8.296e-02 1.004e+00
## Breed2241 -9.282e-02 5.997e-01
## Breed2242 1.611e-01 6.086e-01
## Breed2243 -2.755e-01 2.786e-01
## Breed2245 5.828e-02 7.115e-01
## Breed2246 6.435e-02 4.546e-01
## Breed2247 -3.969e-01 2.274e-01
## Breed2248 -2.313e-01 6.176e-01
## Breed2249 -4.010e-01 5.126e-01
## Breed2250 -3.529e+01 3.355e+07
## Breed2251 -1.482e-01 4.594e-01
## Breed2252 -4.538e-01 3.050e-01
## Breed2254 3.132e-02 2.331e-01
## Breed2256 -1.959e-01 5.802e-01
## Breed2257 -3.486e+01 6.711e+07
## Breed2260 -3.490e+01 6.711e+07
## Breed2262 7.310e-01 1.025e+00
## Breed2263 7.723e-01 1.014e+00
## Breed2264 -3.152e-02 1.322e-01
## Breed2265 -5.620e-02 7.725e-02
## Breed2266 -1.917e-02 6.006e-02
## Breed2267 1.318e-01 5.930e-01
## Breed2268 -6.290e-01 4.497e-01
## Breed2270 -5.528e-01 1.102e+00
## Breed2271 -4.535e-01 6.133e-01
## Breed2272 3.047e-01 1.039e+00
## Breed2274 -3.507e+01 4.745e+07
## Breed2276 -2.561e-01 2.782e-01
## Breed2277 2.779e-01 1.021e+00
## Breed2278 4.716e-01 1.003e+00
## Breed2279 -3.555e+01 6.711e+07
## Breed2282 2.561e-01 6.077e-01
## Breed2283 -1.466e-01 3.643e-01
## Breed2284 -3.503e+01 4.745e+07
## Breed2285 5.822e-02 1.448e-01
## Breed2288 1.164e-01 3.906e-01
## Breed2289 -3.218e-01 1.003e+00
## Breed2290 -3.464e+01 6.711e+07
## Breed2291 -8.203e-01 1.007e+00
## Breed2292 -9.543e-02 1.391e-01
## Breed2293 -3.567e+01 6.711e+07
## Breed2294 1.459e-01 6.166e-01
## Breed2295 -1.021e-02 1.008e+00
## Breed2296 -3.813e-01 1.007e+00
## Breed2299 9.201e-02 1.111e-01
## Breed2300 -1.168e-01 6.243e-01
## Breed2301 -3.551e+01 6.711e+07
## Breed2302 -3.070e-01 1.004e+00
## Breed2303 1.102e-01 2.545e-01
## Breed2304 -1.437e-01 1.003e+00
## Breed2305 -3.349e-01 7.099e-01
## Breed2306 3.253e-01 2.407e-01
## Breed2307 -5.663e-02 4.555e-02
## Gender2 -3.132e-02 2.584e-02
## Gender3 -5.090e-02 4.880e-02
## Color12 -4.438e-02 3.565e-02
## Color13 2.509e-02 5.261e-02
## Color14 -2.907e-02 6.454e-02
## Color15 -2.126e-02 5.344e-02
## Color16 1.057e-02 6.037e-02
## Color17 5.131e-02 6.430e-02
## Color22 2.227e-02 4.734e-02
## Color23 2.976e-02 6.670e-02
## Color24 6.988e-02 6.277e-02
## Color25 2.222e-02 5.424e-02
## Color26 9.245e-03 5.739e-02
## Color27 -1.971e-03 3.583e-02
## Color33 -3.837e-02 1.174e-01
## Color34 -1.342e-02 1.188e-01
## Color35 -1.120e-01 7.804e-02
## Color36 4.077e-02 7.809e-02
## Color37 -9.394e-03 4.020e-02
## MaturitySize 1.951e-02 2.353e-02
## FurLength -9.875e-03 2.523e-02
## Vaccinated2 3.426e-02 3.574e-02
## Vaccinated3 7.586e-02 7.190e-02
## Dewormed2 -3.943e-02 3.306e-02
## Dewormed3 -3.821e-02 7.243e-02
## Sterilized2 1.054e-01 3.895e-02
## Sterilized3 -5.223e-02 5.638e-02
## Health -5.786e-02 6.632e-02
## Quantity 5.714e-03 1.203e-02
## Fee 1.213e-04 1.601e-04
## VideoAmt -4.348e-03 3.695e-02
## PhotoAmt 4.436e-03 3.700e-03
## AdoptionSpeed -8.264e-01 1.229e-02
## StateNameKedah 1.001e-01 1.557e-01
## StateNameKelantan -2.749e-01 3.649e-01
## StateNameKuala Lumpur 9.502e-03 6.649e-02
## StateNameLabuan 3.024e-01 1.006e+00
## StateNameMelaka -9.426e-02 1.710e-01
## StateNameNegeri Sembilan 5.372e-02 1.186e-01
## StateNamePahang -1.483e-01 1.674e-01
## StateNamePerak 6.682e-02 1.014e-01
## StateNamePulau Pinang 2.905e-02 8.309e-02
## StateNameSabah -2.610e-01 3.446e-01
## StateNameSarawak -8.948e-01 7.154e-01
## StateNameSelangor 1.646e-02 6.404e-02
## StateNameTerengganu -1.817e-01 3.129e-01
## MainBreedAffenpinscher -3.543e+01 4.745e+07
## MainBreedAiredale Terrier -3.548e+01 6.711e+07
## MainBreedAkita -8.879e-01 1.229e+00
## MainBreedAmer Bulldog -3.538e+01 6.711e+07
## MainBreedAmer Curl 2.125e-01 4.733e-01
## MainBreedAmer Shorthair 1.784e-02 3.373e-01
## MainBreedAmer Staffordshire Terrier -3.611e+01 3.875e+07
## MainBreedAmer Water Spaniel -3.543e+01 4.745e+07
## MainBreedAmer Wirehair 6.760e-01 6.920e-01
## MainBreedApplehead Siamese 6.079e-01 1.046e+00
## MainBreedAustralian Kelpie -8.707e-01 9.238e-01
## MainBreedAustralian Shepherd -3.525e+01 6.711e+07
## MainBreedAustralian Terrier -1.422e+00 1.228e+00
## MainBreedBalinese 6.036e-01 7.708e-01
## MainBreedBasenji -4.373e-01 1.008e+00
## MainBreedBasset Hound -1.179e+00 8.733e-01
## MainBreedBeagle -9.298e-01 7.266e-01
## MainBreedBearded Collie -5.325e-01 8.219e+07
## MainBreedBedlington Terrier 1.922e-01 1.231e+00
## MainBreedBelgian Shepherd Dog Sheepdog -5.902e-01 1.085e+00
## MainBreedBelgian Shepherd Laekenois -3.386e+01 4.263e+07
## MainBreedBelgian Shepherd Malinois -6.927e-01 7.548e-01
## MainBreedBengal -4.227e-02 3.345e-01
## MainBreedBirman 6.243e-01 1.056e+00
## MainBreedBlack Labrador Retriever -4.388e-01 8.431e-01
## MainBreedBlack Mouth Cur -8.082e-02 9.172e-01
## MainBreedBobtail 1.866e-01 4.786e-01
## MainBreedBombay 3.761e-01 5.753e-01
## MainBreedBorder Collie -6.664e-01 7.802e-01
## MainBreedBoston Terrier -5.269e-01 9.225e-01
## MainBreedBoxer -5.395e-01 8.458e-01
## MainBreedBritish Shorthair -2.090e-02 3.725e-01
## MainBreedBull Terrier -6.132e-01 8.058e-01
## MainBreedBullmastiff -7.244e-01 8.341e-01
## MainBreedBurmese 1.190e-01 4.147e-01
## MainBreedBurmilla -4.935e-01 1.047e+00
## MainBreedCalico -1.149e-01 3.356e-01
## MainBreedCattle Dog -3.636e+01 6.711e+07
## MainBreedCavalier King Charles Spaniel -7.174e-01 1.231e+00
## MainBreedChartreux 6.437e-01 1.050e+00
## MainBreedChausie -3.452e+01 6.711e+07
## MainBreedChihuahua -5.817e-01 7.434e-01
## MainBreedChinese Crested Dog -1.660e+00 1.364e+00
## MainBreedChocolate Labrador Retriever -3.625e+01 6.711e+07
## MainBreedChow Chow -8.542e-01 1.007e+00
## MainBreedCocker Spaniel -6.690e-01 7.451e-01
## MainBreedCollie -7.942e-01 7.550e-01
## MainBreedCoonhound -3.626e+01 4.745e+07
## MainBreedCorgi -8.125e-01 7.822e-01
## MainBreedCymric 8.488e-01 1.060e+00
## MainBreedDachshund -5.682e-01 7.509e-01
## MainBreedDalmatian -8.811e-01 7.480e-01
## MainBreedDilute Calico 2.513e-01 1.045e+00
## MainBreedDilute Tortoiseshell 2.475e-01 1.045e+00
## MainBreedDoberman Pinscher -8.754e-01 7.371e-01
## MainBreedDom Long Hair -4.654e-02 3.099e-01
## MainBreedDom Medium Hair 1.956e-02 3.025e-01
## MainBreedDom Short Hair 4.743e-02 3.018e-01
## MainBreedDutch Shepherd -8.284e-01 1.228e+00
## MainBreedEgyptian Mau 3.082e-01 7.717e-01
## MainBreedEnglish Bulldog -1.157e+00 9.219e-01
## MainBreedEnglish Cocker Spaniel -5.272e-01 8.061e-01
## MainBreedEnglish Pointer -5.787e-02 1.229e+00
## MainBreedEnglish Springer Spaniel -3.621e+01 4.745e+07
## MainBreedExotic Shorthair -5.313e-02 6.526e-01
## MainBreedExtra-Toes Cat (Hemingway Polydactyl) 2.234e-01 7.693e-01
## MainBreedField Spaniel -3.521e+01 6.711e+07
## MainBreedFlat-coated Retriever -3.544e+01 3.875e+07
## MainBreedFox Terrier -7.607e-01 1.236e+00
## MainBreedFoxhound -7.904e-01 1.229e+00
## MainBreedFrench Bulldog -4.186e-01 9.175e-01
## MainBreedGerman Pinscher -7.722e-01 9.170e-01
## MainBreedGerman Shepherd Dog -5.971e-01 7.240e-01
## MainBreedGerman Spitz -6.933e-01 1.007e+00
## MainBreedGlen of Imaal Terrier -4.394e-01 1.006e+00
## MainBreedGolden Retriever -7.951e-01 7.200e-01
## MainBreedGreat Dane -8.484e-01 8.719e-01
## MainBreedGreyhound -1.539e-01 1.205e+00
## MainBreedHavana 7.748e-01 1.058e+00
## MainBreedHimalayan 2.460e-01 6.943e-01
## MainBreedHound -7.323e-01 8.402e-01
## MainBreedHusky -8.195e-01 7.492e-01
## MainBreedIrish Setter -8.889e-01 1.232e+00
## MainBreedIrish Terrier -3.540e+01 6.711e+07
## MainBreedIrish Wolfhound -1.505e-01 1.306e+00
## MainBreedJack Russell Terrier -6.707e-01 7.382e-01
## MainBreedJack Russell Terrier (Parson Russell Terrier) -6.221e-01 1.005e+00
## MainBreedJapanese Bobtail 1.027e-02 7.707e-01
## MainBreedJapanese Chin -3.607e+01 6.711e+07
## MainBreedJavanese -1.777e-01 5.847e-01
## MainBreedKai Dog -3.528e+01 4.745e+07
## MainBreedKorat 5.917e-01 5.901e-01
## MainBreedKuvasz -1.049e+00 1.267e+00
## MainBreedLabrador Retriever -7.477e-01 7.181e-01
## MainBreedLancashire Heeler NA NA
## MainBreedLhasa Apso -4.116e-01 1.005e+00
## MainBreedLowchen -3.611e+01 6.711e+07
## MainBreedMaine Coon -1.600e-01 3.748e-01
## MainBreedMaltese -8.879e-01 7.676e-01
## MainBreedManchester Terrier -5.666e-01 1.004e+00
## MainBreedManx 2.198e-01 5.939e-01
## MainBreedMastiff -1.137e+00 1.233e+00
## MainBreedMiniature Pinscher -6.626e-01 7.306e-01
## MainBreedMixed Breed -7.076e-01 7.118e-01
## MainBreedMountain Dog -3.545e+01 6.711e+07
## MainBreedMunsterlander NA NA
## MainBreedNebelung -3.464e+01 3.875e+07
## MainBreedNorwegian Forest Cat -5.518e-02 6.131e-01
## MainBreedOcicat 3.391e-01 1.269e+00
## MainBreedOld English Sheepdog -3.608e+01 6.711e+07
## MainBreedOrient Long Hair -3.125e-01 4.216e-01
## MainBreedOrient Short Hair 5.556e-02 3.512e-01
## MainBreedOrient Tabby -6.926e-02 7.766e-01
## MainBreedPapillon -1.091e+00 1.005e+00
## MainBreedPekingese -4.402e-01 7.577e-01
## MainBreedPersian -7.041e-02 3.128e-01
## MainBreedPit Bull Terrier -8.871e-01 7.739e-01
## MainBreedPixie-Bob -3.489e+01 6.711e+07
## MainBreedPointer -3.537e+01 6.711e+07
## MainBreedPomeranian -5.621e-01 7.549e-01
## MainBreedPoodle -8.017e-01 7.181e-01
## MainBreedPug -7.694e-01 7.600e-01
## MainBreedRagamuffin -1.975e-01 1.046e+00
## MainBreedRagdoll 3.136e-01 4.179e-01
## MainBreedRat Terrier -5.405e-01 1.003e+00
## MainBreedRetriever -2.689e-01 1.007e+00
## MainBreedRhodesian Ridgeback -1.089e+00 1.238e+00
## MainBreedRottweiler -8.478e-01 7.247e-01
## MainBreedRussian Blue 5.078e-02 3.770e-01
## MainBreedSaint Bernard -8.744e-01 8.426e-01
## MainBreedSamoyed -3.613e+01 6.711e+07
## MainBreedSchnauzer -9.041e-01 7.302e-01
## MainBreedScottish Fold 8.459e-01 1.049e+00
## MainBreedScottish Terrier Scottie 6.408e-02 1.006e+00
## MainBreedSetter -3.600e+01 4.745e+07
## MainBreedShar Pei -6.239e-01 8.078e-01
## MainBreedSheep Dog -3.539e+01 6.711e+07
## MainBreedShepherd -7.859e-01 9.184e-01
## MainBreedShetland Sheepdog Sheltie -6.454e-01 1.005e+00
## MainBreedShiba Inu -5.688e-01 1.228e+00
## MainBreedShih Tzu -6.865e-01 7.155e-01
## MainBreedSiamese -7.926e-03 3.112e-01
## MainBreedSiberian -5.911e-01 7.701e-01
## MainBreedSiberian Husky -6.662e-01 7.508e-01
## MainBreedSilky Terrier -1.048e+00 7.627e-01
## MainBreedSilver -3.462e+01 3.355e+07
## MainBreedSingapura 1.122e-01 5.842e-01
## MainBreedSnowshoe 2.187e-01 1.047e+00
## MainBreedSomali 2.269e-01 5.847e-01
## MainBreedSpaniel -3.531e+01 6.711e+07
## MainBreedSphynx (hairless cat) -8.162e-01 1.049e+00
## MainBreedSpitz -6.965e-01 7.299e-01
## MainBreedStaffordshire Bull Terrier -3.527e+01 6.711e+07
## MainBreedStandard Poodle -4.512e-01 1.229e+00
## MainBreedSwedish Vallhund -3.513e+01 6.711e+07
## MainBreedTabby 2.959e-02 3.095e-01
## MainBreedTerrier -6.498e-01 7.120e-01
## MainBreedTiger 2.528e-02 4.199e-01
## MainBreedTonkinese 1.840e-01 5.908e-01
## MainBreedTorbie 9.910e-01 1.050e+00
## MainBreedTortoiseshell 1.488e-01 3.585e-01
## MainBreedToy Fox Terrier -6.897e-01 1.004e+00
## MainBreedTurkish Angora 6.139e-01 5.927e-01
## MainBreedTurkish Van -6.306e-01 7.692e-01
## MainBreedTuxedo -1.465e-01 3.558e-01
## MainBreedWeimaraner -3.565e+01 3.875e+07
## MainBreedWelsh Corgi 3.195e-01 1.276e+00
## MainBreedWest Highland White Terrier Westie -6.535e-01 9.278e-01
## MainBreedWheaten Terrier -3.617e+01 4.745e+07
## MainBreedWhippet -1.082e+00 1.232e+00
## MainBreedWhite German Shepherd -4.286e-01 1.230e+00
## MainBreedWirehaired Terrier -1.555e-01 1.230e+00
## MainBreedYellow Labrador Retriever -8.670e-01 9.188e-01
## MainBreedYorkshire Terrier Yorkie -7.118e-01 8.410e-01
## has_name1 -4.575e-04 4.446e-02
## pure_breed1 NA NA
## z value Pr(>|z|)
## (Intercept) 2.257 0.02402 *
## Type2 -1.214 0.22492
## Age -0.485 0.62798
## Breed21 0.564 0.57297
## Breed22 -0.286 0.77479
## Breed24 -0.190 0.84962
## Breed25 -0.133 0.89403
## Breed210 0.425 0.67089
## Breed214 0.000 1.00000
## Breed216 0.337 0.73647
## Breed217 0.000 1.00000
## Breed218 0.153 0.87808
## Breed219 0.500 0.61713
## Breed220 0.254 0.79921
## Breed221 0.000 1.00000
## Breed224 -0.749 0.45390
## Breed225 0.000 1.00000
## Breed226 1.547 0.12177
## Breed236 0.000 1.00000
## Breed239 0.448 0.65396
## Breed240 0.000 1.00000
## Breed244 0.418 0.67607
## Breed249 0.288 0.77312
## Breed250 0.520 0.60319
## Breed258 0.000 1.00000
## Breed260 -0.210 0.83387
## Breed265 0.091 0.92782
## Breed269 0.083 0.93352
## Breed270 0.094 0.92540
## Breed272 0.020 0.98412
## Breed275 0.167 0.86699
## Breed276 -0.905 0.36535
## Breed278 0.171 0.86412
## Breed283 0.728 0.46681
## Breed296 0.703 0.48191
## Breed298 0.938 0.34833
## Breed2102 0.396 0.69206
## Breed2103 0.558 0.57689
## Breed2104 0.000 1.00000
## Breed2109 -1.249 0.21170
## Breed2111 0.000 1.00000
## Breed2115 -0.007 0.99472
## Breed2117 -0.766 0.44370
## Breed2119 0.567 0.57067
## Breed2122 0.000 1.00000
## Breed2128 0.373 0.70943
## Breed2129 0.106 0.91530
## Breed2130 -0.106 0.91545
## Breed2141 -0.950 0.34228
## Breed2146 0.000 1.00000
## Breed2147 0.493 0.62187
## Breed2150 0.491 0.62365
## Breed2152 -0.525 0.59976
## Breed2155 -0.052 0.95815
## Breed2159 0.000 1.00000
## Breed2167 0.000 1.00000
## Breed2169 -0.255 0.79879
## Breed2173 -0.042 0.96621
## Breed2176 0.000 1.00000
## Breed2178 0.295 0.76763
## Breed2179 0.161 0.87198
## Breed2182 0.000 1.00000
## Breed2187 0.009 0.99256
## Breed2188 -0.149 0.88128
## Breed2189 -0.186 0.85207
## Breed2190 0.000 1.00000
## Breed2192 -0.423 0.67242
## Breed2195 -0.926 0.35428
## Breed2200 0.261 0.79427
## Breed2201 -0.601 0.54770
## Breed2202 -0.135 0.89268
## Breed2203 0.602 0.54703
## Breed2204 0.000 1.00000
## Breed2205 -0.202 0.83970
## Breed2206 -0.678 0.49755
## Breed2207 0.097 0.92254
## Breed2210 0.572 0.56731
## Breed2212 0.318 0.75026
## Breed2213 1.036 0.30023
## Breed2218 -0.556 0.57790
## Breed2227 0.263 0.79285
## Breed2228 0.980 0.32703
## Breed2237 0.832 0.40558
## Breed2239 -0.026 0.97949
## Breed2240 -0.083 0.93417
## Breed2241 -0.155 0.87699
## Breed2242 0.265 0.79126
## Breed2243 -0.989 0.32271
## Breed2245 0.082 0.93472
## Breed2246 0.142 0.88742
## Breed2247 -1.745 0.08090 .
## Breed2248 -0.374 0.70810
## Breed2249 -0.782 0.43411
## Breed2250 0.000 1.00000
## Breed2251 -0.323 0.74699
## Breed2252 -1.488 0.13683
## Breed2254 0.134 0.89313
## Breed2256 -0.338 0.73562
## Breed2257 0.000 1.00000
## Breed2260 0.000 1.00000
## Breed2262 0.713 0.47590
## Breed2263 0.762 0.44608
## Breed2264 -0.238 0.81157
## Breed2265 -0.727 0.46693
## Breed2266 -0.319 0.74959
## Breed2267 0.222 0.82414
## Breed2268 -1.399 0.16188
## Breed2270 -0.502 0.61599
## Breed2271 -0.739 0.45971
## Breed2272 0.293 0.76941
## Breed2274 0.000 1.00000
## Breed2276 -0.921 0.35716
## Breed2277 0.272 0.78553
## Breed2278 0.470 0.63829
## Breed2279 0.000 1.00000
## Breed2282 0.421 0.67345
## Breed2283 -0.403 0.68727
## Breed2284 0.000 1.00000
## Breed2285 0.402 0.68757
## Breed2288 0.298 0.76571
## Breed2289 -0.321 0.74841
## Breed2290 0.000 1.00000
## Breed2291 -0.815 0.41519
## Breed2292 -0.686 0.49277
## Breed2293 0.000 1.00000
## Breed2294 0.237 0.81303
## Breed2295 -0.010 0.99192
## Breed2296 -0.379 0.70486
## Breed2299 0.828 0.40778
## Breed2300 -0.187 0.85161
## Breed2301 0.000 1.00000
## Breed2302 -0.306 0.75987
## Breed2303 0.433 0.66511
## Breed2304 -0.143 0.88608
## Breed2305 -0.472 0.63709
## Breed2306 1.351 0.17657
## Breed2307 -1.243 0.21375
## Gender2 -1.212 0.22545
## Gender3 -1.043 0.29688
## Color12 -1.245 0.21318
## Color13 0.477 0.63338
## Color14 -0.450 0.65241
## Color15 -0.398 0.69071
## Color16 0.175 0.86101
## Color17 0.798 0.42487
## Color22 0.470 0.63803
## Color23 0.446 0.65545
## Color24 1.113 0.26558
## Color25 0.410 0.68204
## Color26 0.161 0.87203
## Color27 -0.055 0.95613
## Color33 -0.327 0.74379
## Color34 -0.113 0.91001
## Color35 -1.435 0.15116
## Color36 0.522 0.60161
## Color37 -0.234 0.81524
## MaturitySize 0.829 0.40711
## FurLength -0.391 0.69551
## Vaccinated2 0.959 0.33776
## Vaccinated3 1.055 0.29136
## Dewormed2 -1.193 0.23296
## Dewormed3 -0.528 0.59781
## Sterilized2 2.707 0.00679 **
## Sterilized3 -0.926 0.35422
## Health -0.872 0.38298
## Quantity 0.475 0.63469
## Fee 0.758 0.44867
## VideoAmt -0.118 0.90632
## PhotoAmt 1.199 0.23051
## AdoptionSpeed -67.236 < 2e-16 ***
## StateNameKedah 0.643 0.52011
## StateNameKelantan -0.753 0.45131
## StateNameKuala Lumpur 0.143 0.88636
## StateNameLabuan 0.301 0.76374
## StateNameMelaka -0.551 0.58148
## StateNameNegeri Sembilan 0.453 0.65058
## StateNamePahang -0.886 0.37555
## StateNamePerak 0.659 0.51002
## StateNamePulau Pinang 0.350 0.72659
## StateNameSabah -0.757 0.44878
## StateNameSarawak -1.251 0.21101
## StateNameSelangor 0.257 0.79719
## StateNameTerengganu -0.581 0.56150
## MainBreedAffenpinscher 0.000 1.00000
## MainBreedAiredale Terrier 0.000 1.00000
## MainBreedAkita -0.723 0.46989
## MainBreedAmer Bulldog 0.000 1.00000
## MainBreedAmer Curl 0.449 0.65340
## MainBreedAmer Shorthair 0.053 0.95782
## MainBreedAmer Staffordshire Terrier 0.000 1.00000
## MainBreedAmer Water Spaniel 0.000 1.00000
## MainBreedAmer Wirehair 0.977 0.32868
## MainBreedApplehead Siamese 0.581 0.56126
## MainBreedAustralian Kelpie -0.943 0.34593
## MainBreedAustralian Shepherd 0.000 1.00000
## MainBreedAustralian Terrier -1.158 0.24688
## MainBreedBalinese 0.783 0.43357
## MainBreedBasenji -0.434 0.66434
## MainBreedBasset Hound -1.350 0.17695
## MainBreedBeagle -1.280 0.20063
## MainBreedBearded Collie 0.000 1.00000
## MainBreedBedlington Terrier 0.156 0.87591
## MainBreedBelgian Shepherd Dog Sheepdog -0.544 0.58636
## MainBreedBelgian Shepherd Laekenois 0.000 1.00000
## MainBreedBelgian Shepherd Malinois -0.918 0.35878
## MainBreedBengal -0.126 0.89945
## MainBreedBirman 0.591 0.55440
## MainBreedBlack Labrador Retriever -0.520 0.60272
## MainBreedBlack Mouth Cur -0.088 0.92978
## MainBreedBobtail 0.390 0.69663
## MainBreedBombay 0.654 0.51326
## MainBreedBorder Collie -0.854 0.39307
## MainBreedBoston Terrier -0.571 0.56788
## MainBreedBoxer -0.638 0.52359
## MainBreedBritish Shorthair -0.056 0.95526
## MainBreedBull Terrier -0.761 0.44666
## MainBreedBullmastiff -0.868 0.38516
## MainBreedBurmese 0.287 0.77413
## MainBreedBurmilla -0.472 0.63727
## MainBreedCalico -0.342 0.73214
## MainBreedCattle Dog 0.000 1.00000
## MainBreedCavalier King Charles Spaniel -0.583 0.56022
## MainBreedChartreux 0.613 0.53996
## MainBreedChausie 0.000 1.00000
## MainBreedChihuahua -0.782 0.43393
## MainBreedChinese Crested Dog -1.217 0.22366
## MainBreedChocolate Labrador Retriever 0.000 1.00000
## MainBreedChow Chow -0.849 0.39615
## MainBreedCocker Spaniel -0.898 0.36921
## MainBreedCollie -1.052 0.29283
## MainBreedCoonhound 0.000 1.00000
## MainBreedCorgi -1.039 0.29894
## MainBreedCymric 0.801 0.42312
## MainBreedDachshund -0.757 0.44927
## MainBreedDalmatian -1.178 0.23886
## MainBreedDilute Calico 0.241 0.80988
## MainBreedDilute Tortoiseshell 0.237 0.81275
## MainBreedDoberman Pinscher -1.188 0.23498
## MainBreedDom Long Hair -0.150 0.88060
## MainBreedDom Medium Hair 0.065 0.94843
## MainBreedDom Short Hair 0.157 0.87512
## MainBreedDutch Shepherd -0.674 0.50000
## MainBreedEgyptian Mau 0.399 0.68966
## MainBreedEnglish Bulldog -1.255 0.20960
## MainBreedEnglish Cocker Spaniel -0.654 0.51312
## MainBreedEnglish Pointer -0.047 0.96245
## MainBreedEnglish Springer Spaniel 0.000 1.00000
## MainBreedExotic Shorthair -0.081 0.93512
## MainBreedExtra-Toes Cat (Hemingway Polydactyl) 0.290 0.77148
## MainBreedField Spaniel 0.000 1.00000
## MainBreedFlat-coated Retriever 0.000 1.00000
## MainBreedFox Terrier -0.616 0.53822
## MainBreedFoxhound -0.643 0.52012
## MainBreedFrench Bulldog -0.456 0.64821
## MainBreedGerman Pinscher -0.842 0.39972
## MainBreedGerman Shepherd Dog -0.825 0.40958
## MainBreedGerman Spitz -0.689 0.49111
## MainBreedGlen of Imaal Terrier -0.437 0.66231
## MainBreedGolden Retriever -1.104 0.26947
## MainBreedGreat Dane -0.973 0.33050
## MainBreedGreyhound -0.128 0.89834
## MainBreedHavana 0.732 0.46418
## MainBreedHimalayan 0.354 0.72309
## MainBreedHound -0.872 0.38344
## MainBreedHusky -1.094 0.27408
## MainBreedIrish Setter -0.721 0.47072
## MainBreedIrish Terrier 0.000 1.00000
## MainBreedIrish Wolfhound -0.115 0.90827
## MainBreedJack Russell Terrier -0.909 0.36360
## MainBreedJack Russell Terrier (Parson Russell Terrier) -0.619 0.53612
## MainBreedJapanese Bobtail 0.013 0.98936
## MainBreedJapanese Chin 0.000 1.00000
## MainBreedJavanese -0.304 0.76115
## MainBreedKai Dog 0.000 1.00000
## MainBreedKorat 1.003 0.31604
## MainBreedKuvasz -0.828 0.40763
## MainBreedLabrador Retriever -1.041 0.29779
## MainBreedLancashire Heeler NA NA
## MainBreedLhasa Apso -0.410 0.68201
## MainBreedLowchen 0.000 1.00000
## MainBreedMaine Coon -0.427 0.66951
## MainBreedMaltese -1.157 0.24740
## MainBreedManchester Terrier -0.565 0.57238
## MainBreedManx 0.370 0.71134
## MainBreedMastiff -0.922 0.35647
## MainBreedMiniature Pinscher -0.907 0.36449
## MainBreedMixed Breed -0.994 0.32017
## MainBreedMountain Dog 0.000 1.00000
## MainBreedMunsterlander NA NA
## MainBreedNebelung 0.000 1.00000
## MainBreedNorwegian Forest Cat -0.090 0.92828
## MainBreedOcicat 0.267 0.78931
## MainBreedOld English Sheepdog 0.000 1.00000
## MainBreedOrient Long Hair -0.741 0.45852
## MainBreedOrient Short Hair 0.158 0.87428
## MainBreedOrient Tabby -0.089 0.92894
## MainBreedPapillon -1.085 0.27778
## MainBreedPekingese -0.581 0.56131
## MainBreedPersian -0.225 0.82193
## MainBreedPit Bull Terrier -1.146 0.25170
## MainBreedPixie-Bob 0.000 1.00000
## MainBreedPointer 0.000 1.00000
## MainBreedPomeranian -0.745 0.45651
## MainBreedPoodle -1.116 0.26427
## MainBreedPug -1.012 0.31134
## MainBreedRagamuffin -0.189 0.85028
## MainBreedRagdoll 0.750 0.45301
## MainBreedRat Terrier -0.539 0.59006
## MainBreedRetriever -0.267 0.78948
## MainBreedRhodesian Ridgeback -0.880 0.37883
## MainBreedRottweiler -1.170 0.24207
## MainBreedRussian Blue 0.135 0.89285
## MainBreedSaint Bernard -1.038 0.29941
## MainBreedSamoyed 0.000 1.00000
## MainBreedSchnauzer -1.238 0.21565
## MainBreedScottish Fold 0.806 0.42008
## MainBreedScottish Terrier Scottie 0.064 0.94920
## MainBreedSetter 0.000 1.00000
## MainBreedShar Pei -0.772 0.43992
## MainBreedSheep Dog 0.000 1.00000
## MainBreedShepherd -0.856 0.39212
## MainBreedShetland Sheepdog Sheltie -0.642 0.52081
## MainBreedShiba Inu -0.463 0.64321
## MainBreedShih Tzu -0.959 0.33733
## MainBreedSiamese -0.025 0.97968
## MainBreedSiberian -0.768 0.44274
## MainBreedSiberian Husky -0.887 0.37495
## MainBreedSilky Terrier -1.374 0.16932
## MainBreedSilver 0.000 1.00000
## MainBreedSingapura 0.192 0.84766
## MainBreedSnowshoe 0.209 0.83456
## MainBreedSomali 0.388 0.69803
## MainBreedSpaniel 0.000 1.00000
## MainBreedSphynx (hairless cat) -0.778 0.43667
## MainBreedSpitz -0.954 0.33993
## MainBreedStaffordshire Bull Terrier 0.000 1.00000
## MainBreedStandard Poodle -0.367 0.71359
## MainBreedSwedish Vallhund 0.000 1.00000
## MainBreedTabby 0.096 0.92385
## MainBreedTerrier -0.913 0.36145
## MainBreedTiger 0.060 0.95199
## MainBreedTonkinese 0.311 0.75550
## MainBreedTorbie 0.944 0.34518
## MainBreedTortoiseshell 0.415 0.67814
## MainBreedToy Fox Terrier -0.687 0.49203
## MainBreedTurkish Angora 1.036 0.30034
## MainBreedTurkish Van -0.820 0.41231
## MainBreedTuxedo -0.412 0.68049
## MainBreedWeimaraner 0.000 1.00000
## MainBreedWelsh Corgi 0.250 0.80228
## MainBreedWest Highland White Terrier Westie -0.704 0.48119
## MainBreedWheaten Terrier 0.000 1.00000
## MainBreedWhippet -0.878 0.37992
## MainBreedWhite German Shepherd -0.349 0.72739
## MainBreedWirehaired Terrier -0.126 0.89936
## MainBreedYellow Labrador Retriever -0.944 0.34534
## MainBreedYorkshire Terrier Yorkie -0.846 0.39736
## has_name1 -0.010 0.99179
## pure_breed1 NA NA
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for Negative Binomial(23950.02) family taken to be 1)
##
## Null deviance: 10362.7 on 14987 degrees of freedom
## Residual deviance: 4204.6 on 14632 degrees of freedom
## (3953 observations deleted due to missingness)
## AIC: 19991
##
## Number of Fisher Scoring iterations: 1
##
##
## Theta: 23950
## Std. Err.: 27269
## Warning while fitting theta: alternation limit reached
##
## 2 x log-likelihood: -19276.89Variables with high amount of factors are dropped.
Dividing into train and test set
Data is now partitioned into 70% train and 30% test.
set.seed(100)
index = sample(1:nrow(newtr_te), 0.7*nrow(newtr_te))
train1 = newtr_te[index,] # Create the training data
test1 = newtr_te[-index,] # Create the test data
dim(train1)## [1] 13258 17dim(test1)## [1] 5683 17Negative binomial model:
modelnegb1 <- glm.nb(High ~ ., data = train1)summary(modelnegb1)##
## Call:
## glm.nb(formula = High ~ ., data = train1, init.theta = 16669.18195,
## link = log)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -1.5052 -0.9488 -0.1298 0.5660 1.5594
##
## Coefficients: (1 not defined because of singularities)
## Estimate Std. Error
## (Intercept) -6.631e-01 7.002e-01
## Type2 -3.317e-01 6.040e-01
## Age -7.170e-03 1.165e-03
## Gender2 -1.136e-01 3.067e-02
## Gender3 -1.353e-01 5.820e-02
## Color12 -2.006e-02 3.640e-02
## Color13 1.861e-02 5.994e-02
## Color14 -1.806e-01 7.463e-02
## Color15 7.820e-02 5.997e-02
## Color16 3.520e-02 6.857e-02
## Color17 8.234e-02 6.831e-02
## MaturitySize -1.509e-02 2.827e-02
## FurLength 7.439e-02 2.886e-02
## Vaccinated2 1.476e-01 4.169e-02
## Vaccinated3 3.792e-02 8.508e-02
## Dewormed2 -1.612e-02 3.885e-02
## Dewormed3 -3.651e-02 8.565e-02
## Sterilized2 4.047e-01 4.648e-02
## Sterilized3 2.403e-01 6.616e-02
## Health -1.618e-01 7.724e-02
## Quantity -3.287e-02 1.481e-02
## Fee -3.873e-04 2.026e-04
## PhotoAmt 1.577e-03 4.182e-03
## MainBreedAffenpinscher -3.573e+01 6.711e+07
## MainBreedAiredale Terrier -3.674e+01 6.711e+07
## MainBreedAkita 3.199e-02 1.216e+00
## MainBreedAmer Bulldog -3.616e+01 6.711e+07
## MainBreedAmer Curl 4.082e-01 5.075e-01
## MainBreedAmer Shorthair 1.087e-01 3.778e-01
## MainBreedAmer Staffordshire Terrier -3.580e+01 6.711e+07
## MainBreedAmer Water Spaniel -3.681e+01 4.745e+07
## MainBreedAmer Wirehair 5.527e-01 6.680e-01
## MainBreedApplehead Siamese 3.793e-01 1.055e+00
## MainBreedAustralian Kelpie -8.117e-01 9.881e-01
## MainBreedAustralian Shepherd -3.629e+01 6.711e+07
## MainBreedAustralian Terrier -1.183e+00 1.216e+00
## MainBreedBalinese 4.808e-02 7.830e-01
## MainBreedBasenji -3.567e-01 9.887e-01
## MainBreedBasset Hound -7.062e-02 1.216e+00
## MainBreedBeagle 1.370e-01 7.115e-01
## MainBreedBearded Collie -3.632e+01 6.711e+07
## MainBreedBedlington Terrier 1.366e+00 1.220e+00
## MainBreedBelgian Shepherd Dog Sheepdog 6.073e-01 9.899e-01
## MainBreedBelgian Shepherd Laekenois -4.609e-02 1.110e+00
## MainBreedBelgian Shepherd Malinois 8.468e-02 7.535e-01
## MainBreedBengal 3.491e-01 3.766e-01
## MainBreedBirman 2.252e-01 1.056e+00
## MainBreedBlack Labrador Retriever 2.706e-01 8.540e-01
## MainBreedBlack Mouth Cur 3.108e-01 9.003e-01
## MainBreedBobtail -9.414e-01 7.823e-01
## MainBreedBombay -2.214e-01 6.674e-01
## MainBreedBorder Collie -5.668e-02 7.532e-01
## MainBreedBoston Terrier 4.531e-01 9.010e-01
## MainBreedBoxer -2.878e-02 9.003e-01
## MainBreedBritish Shorthair 3.622e-01 4.606e-01
## MainBreedBull Terrier -4.019e-01 8.523e-01
## MainBreedBullmastiff -1.611e-02 8.229e-01
## MainBreedBurmese 1.223e-01 5.043e-01
## MainBreedBurmilla 2.725e-01 1.056e+00
## MainBreedCalico 7.288e-02 3.781e-01
## MainBreedCattle Dog -3.679e+01 6.711e+07
## MainBreedCavalier King Charles Spaniel 6.098e-01 1.219e+00
## MainBreedChartreux 2.980e-01 1.057e+00
## MainBreedChihuahua 2.135e-01 7.405e-01
## MainBreedChinese Crested Dog 9.641e-01 1.216e+00
## MainBreedChocolate Labrador Retriever -3.654e+01 6.711e+07
## MainBreedChow Chow 7.900e-01 9.902e-01
## MainBreedCocker Spaniel 3.817e-01 7.304e-01
## MainBreedCollie 2.745e-01 7.447e-01
## MainBreedCoonhound -3.654e+01 4.745e+07
## MainBreedCorgi -8.464e-02 8.225e-01
## MainBreedCymric -3.635e+01 6.711e+07
## MainBreedDachshund 2.552e-01 7.593e-01
## MainBreedDalmatian 7.275e-02 7.342e-01
## MainBreedDilute Calico 5.421e-01 1.055e+00
## MainBreedDilute Tortoiseshell 2.292e-01 1.057e+00
## MainBreedDoberman Pinscher 7.621e-02 7.202e-01
## MainBreedDom Long Hair 3.165e-01 3.461e-01
## MainBreedDom Medium Hair 1.998e-01 3.371e-01
## MainBreedDom Short Hair 1.783e-01 3.352e-01
## MainBreedEgyptian Mau 5.710e-01 7.830e-01
## MainBreedEnglish Bulldog -2.136e-01 1.216e+00
## MainBreedEnglish Cocker Spaniel 6.649e-01 8.234e-01
## MainBreedEnglish Springer Spaniel -3.651e+01 6.711e+07
## MainBreedExotic Shorthair 1.027e-01 7.825e-01
## MainBreedExtra-Toes Cat (Hemingway Polydactyl) 8.192e-01 7.829e-01
## MainBreedField Spaniel -3.671e+01 6.711e+07
## MainBreedFlat-coated Retriever -3.592e+01 3.875e+07
## MainBreedFox Terrier -1.949e-01 1.217e+00
## MainBreedFrench Bulldog 9.847e-01 9.927e-01
## MainBreedGerman Pinscher 1.062e-01 9.001e-01
## MainBreedGerman Shepherd Dog 8.147e-02 7.080e-01
## MainBreedGerman Spitz -3.616e+01 6.711e+07
## MainBreedGlen of Imaal Terrier 7.701e-01 9.905e-01
## MainBreedGolden Retriever 2.525e-01 7.022e-01
## MainBreedGreat Dane 8.856e-01 8.549e-01
## MainBreedHimalayan 7.613e-01 6.681e-01
## MainBreedHound 9.870e-02 8.524e-01
## MainBreedHusky 9.661e-02 7.443e-01
## MainBreedIrish Setter -3.581e+01 6.711e+07
## MainBreedIrish Terrier -3.645e+01 6.711e+07
## MainBreedIrish Wolfhound 8.985e-01 1.216e+00
## MainBreedJack Russell Terrier 1.848e-02 7.225e-01
## MainBreedJack Russell Terrier (Parson Russell Terrier) 1.303e-01 9.896e-01
## MainBreedJapanese Bobtail 1.880e-01 1.056e+00
## MainBreedJapanese Chin -3.586e+01 6.711e+07
## MainBreedJavanese -6.747e-02 6.675e-01
## MainBreedKai Dog -3.595e+01 6.711e+07
## MainBreedKorat 6.467e-01 6.690e-01
## MainBreedKuvasz 6.200e-01 1.217e+00
## MainBreedLabrador Retriever 1.326e-02 6.996e-01
## MainBreedLhasa Apso 7.390e-01 1.218e+00
## MainBreedMaine Coon 3.185e-01 4.198e-01
## MainBreedMaltese 3.627e-01 7.620e-01
## MainBreedManchester Terrier 2.736e-01 1.215e+00
## MainBreedManx 1.166e-01 6.676e-01
## MainBreedMastiff -9.823e-02 1.217e+00
## MainBreedMiniature Pinscher 7.107e-02 7.213e-01
## MainBreedMixed Breed -3.467e-01 6.901e-01
## MainBreedMountain Dog -3.676e+01 6.711e+07
## MainBreedMunsterlander 4.284e-01 1.216e+00
## MainBreedNebelung -3.620e+01 4.745e+07
## MainBreedNorwegian Forest Cat 9.390e-01 6.039e-01
## MainBreedOcicat 1.241e+00 1.057e+00
## MainBreedOld English Sheepdog -3.572e+01 6.711e+07
## MainBreedOrient Long Hair 6.096e-01 4.729e-01
## MainBreedOrient Short Hair 5.733e-02 3.961e-01
## MainBreedOrient Tabby -3.984e-01 7.826e-01
## MainBreedPekingese 6.077e-01 7.767e-01
## MainBreedPersian 4.092e-01 3.495e-01
## MainBreedPit Bull Terrier -2.124e-01 7.871e-01
## MainBreedPixie-Bob -3.626e+01 6.711e+07
## MainBreedPomeranian 4.039e-01 7.490e-01
## MainBreedPoodle 3.226e-01 7.015e-01
## MainBreedPug 4.234e-01 7.759e-01
## MainBreedRagdoll 6.761e-01 4.508e-01
## MainBreedRetriever -1.124e-01 9.887e-01
## MainBreedRhodesian Ridgeback 2.025e-01 1.216e+00
## MainBreedRottweiler 2.412e-01 7.081e-01
## MainBreedRussian Blue 4.827e-01 4.240e-01
## MainBreedSaint Bernard 6.442e-01 8.242e-01
## MainBreedSamoyed -3.583e+01 6.711e+07
## MainBreedSchnauzer 1.923e-01 7.155e-01
## MainBreedScottish Terrier Scottie 6.998e-01 1.218e+00
## MainBreedSetter -3.632e+01 4.745e+07
## MainBreedShar Pei 1.946e-01 8.020e-01
## MainBreedShepherd -1.919e-01 9.889e-01
## MainBreedShetland Sheepdog Sheltie 6.923e-02 9.890e-01
## MainBreedShiba Inu -3.793e-01 1.216e+00
## MainBreedShih Tzu 4.171e-01 6.959e-01
## MainBreedSiamese 4.284e-01 3.470e-01
## MainBreedSiberian Husky 2.540e-01 7.536e-01
## MainBreedSilky Terrier 1.823e-01 7.880e-01
## MainBreedSilver -3.591e+01 3.875e+07
## MainBreedSingapura -4.462e-01 7.822e-01
## MainBreedSnowshoe -3.378e-01 1.055e+00
## MainBreedSomali 5.121e-01 6.676e-01
## MainBreedSpaniel -3.576e+01 6.711e+07
## MainBreedSphynx (hairless cat) 1.059e+00 1.060e+00
## MainBreedSpitz -3.169e-02 7.140e-01
## MainBreedStaffordshire Bull Terrier -3.542e+01 6.711e+07
## MainBreedStandard Poodle -1.483e-01 1.217e+00
## MainBreedTabby 3.068e-01 3.443e-01
## MainBreedTerrier -2.404e-01 6.989e-01
## MainBreedTiger 1.375e-01 4.864e-01
## MainBreedTonkinese 7.290e-01 7.828e-01
## MainBreedTorbie 1.475e+00 1.056e+00
## MainBreedTortoiseshell 5.209e-01 4.176e-01
## MainBreedToy Fox Terrier -4.148e-01 1.215e+00
## MainBreedTurkish Angora 6.779e-02 7.824e-01
## MainBreedTurkish Van -9.840e-01 1.055e+00
## MainBreedTuxedo 1.473e-01 4.130e-01
## MainBreedWeimaraner -3.656e+01 4.745e+07
## MainBreedWelsh Corgi 1.101e+00 1.216e+00
## MainBreedWest Highland White Terrier Westie 4.050e-01 9.029e-01
## MainBreedWheaten Terrier -3.573e+01 4.745e+07
## MainBreedWhite German Shepherd 8.976e-02 1.219e+00
## MainBreedWirehaired Terrier 4.629e-01 1.216e+00
## MainBreedYellow Labrador Retriever -9.944e-01 9.903e-01
## MainBreedYorkshire Terrier Yorkie 7.732e-01 9.016e-01
## has_name1 1.651e-02 5.168e-02
## pure_breed1 NA NA
## z value Pr(>|z|)
## (Intercept) -0.947 0.343676
## Type2 -0.549 0.582918
## Age -6.154 7.55e-10 ***
## Gender2 -3.705 0.000212 ***
## Gender3 -2.325 0.020080 *
## Color12 -0.551 0.581528
## Color13 0.311 0.756160
## Color14 -2.420 0.015542 *
## Color15 1.304 0.192202
## Color16 0.513 0.607700
## Color17 1.205 0.228050
## MaturitySize -0.534 0.593480
## FurLength 2.578 0.009942 **
## Vaccinated2 3.541 0.000399 ***
## Vaccinated3 0.446 0.655801
## Dewormed2 -0.415 0.678103
## Dewormed3 -0.426 0.669877
## Sterilized2 8.707 < 2e-16 ***
## Sterilized3 3.633 0.000281 ***
## Health -2.095 0.036188 *
## Quantity -2.219 0.026499 *
## Fee -1.911 0.055996 .
## PhotoAmt 0.377 0.706079
## MainBreedAffenpinscher 0.000 1.000000
## MainBreedAiredale Terrier 0.000 1.000000
## MainBreedAkita 0.026 0.979012
## MainBreedAmer Bulldog 0.000 1.000000
## MainBreedAmer Curl 0.804 0.421284
## MainBreedAmer Shorthair 0.288 0.773495
## MainBreedAmer Staffordshire Terrier 0.000 1.000000
## MainBreedAmer Water Spaniel 0.000 0.999999
## MainBreedAmer Wirehair 0.827 0.407971
## MainBreedApplehead Siamese 0.359 0.719264
## MainBreedAustralian Kelpie -0.821 0.411391
## MainBreedAustralian Shepherd 0.000 1.000000
## MainBreedAustralian Terrier -0.973 0.330613
## MainBreedBalinese 0.061 0.951037
## MainBreedBasenji -0.361 0.718293
## MainBreedBasset Hound -0.058 0.953675
## MainBreedBeagle 0.193 0.847318
## MainBreedBearded Collie 0.000 1.000000
## MainBreedBedlington Terrier 1.120 0.262830
## MainBreedBelgian Shepherd Dog Sheepdog 0.613 0.539596
## MainBreedBelgian Shepherd Laekenois -0.042 0.966877
## MainBreedBelgian Shepherd Malinois 0.112 0.910521
## MainBreedBengal 0.927 0.353944
## MainBreedBirman 0.213 0.831048
## MainBreedBlack Labrador Retriever 0.317 0.751392
## MainBreedBlack Mouth Cur 0.345 0.729952
## MainBreedBobtail -1.203 0.228800
## MainBreedBombay -0.332 0.740152
## MainBreedBorder Collie -0.075 0.940007
## MainBreedBoston Terrier 0.503 0.615015
## MainBreedBoxer -0.032 0.974495
## MainBreedBritish Shorthair 0.786 0.431644
## MainBreedBull Terrier -0.472 0.637269
## MainBreedBullmastiff -0.020 0.984383
## MainBreedBurmese 0.242 0.808444
## MainBreedBurmilla 0.258 0.796286
## MainBreedCalico 0.193 0.847162
## MainBreedCattle Dog 0.000 1.000000
## MainBreedCavalier King Charles Spaniel 0.500 0.616895
## MainBreedChartreux 0.282 0.778081
## MainBreedChihuahua 0.288 0.773109
## MainBreedChinese Crested Dog 0.793 0.427949
## MainBreedChocolate Labrador Retriever 0.000 1.000000
## MainBreedChow Chow 0.798 0.424952
## MainBreedCocker Spaniel 0.523 0.601250
## MainBreedCollie 0.369 0.712416
## MainBreedCoonhound 0.000 0.999999
## MainBreedCorgi -0.103 0.918037
## MainBreedCymric 0.000 1.000000
## MainBreedDachshund 0.336 0.736763
## MainBreedDalmatian 0.099 0.921071
## MainBreedDilute Calico 0.514 0.607295
## MainBreedDilute Tortoiseshell 0.217 0.828281
## MainBreedDoberman Pinscher 0.106 0.915731
## MainBreedDom Long Hair 0.914 0.360507
## MainBreedDom Medium Hair 0.593 0.553357
## MainBreedDom Short Hair 0.532 0.594828
## MainBreedEgyptian Mau 0.729 0.465850
## MainBreedEnglish Bulldog -0.176 0.860542
## MainBreedEnglish Cocker Spaniel 0.807 0.419395
## MainBreedEnglish Springer Spaniel 0.000 1.000000
## MainBreedExotic Shorthair 0.131 0.895616
## MainBreedExtra-Toes Cat (Hemingway Polydactyl) 1.046 0.295392
## MainBreedField Spaniel 0.000 1.000000
## MainBreedFlat-coated Retriever 0.000 0.999999
## MainBreedFox Terrier -0.160 0.872699
## MainBreedFrench Bulldog 0.992 0.321202
## MainBreedGerman Pinscher 0.118 0.906051
## MainBreedGerman Shepherd Dog 0.115 0.908396
## MainBreedGerman Spitz 0.000 1.000000
## MainBreedGlen of Imaal Terrier 0.777 0.436864
## MainBreedGolden Retriever 0.360 0.719219
## MainBreedGreat Dane 1.036 0.300221
## MainBreedHimalayan 1.140 0.254491
## MainBreedHound 0.116 0.907823
## MainBreedHusky 0.130 0.896731
## MainBreedIrish Setter 0.000 1.000000
## MainBreedIrish Terrier 0.000 1.000000
## MainBreedIrish Wolfhound 0.739 0.459864
## MainBreedJack Russell Terrier 0.026 0.979590
## MainBreedJack Russell Terrier (Parson Russell Terrier) 0.132 0.895267
## MainBreedJapanese Bobtail 0.178 0.858775
## MainBreedJapanese Chin 0.000 1.000000
## MainBreedJavanese -0.101 0.919491
## MainBreedKai Dog 0.000 1.000000
## MainBreedKorat 0.967 0.333719
## MainBreedKuvasz 0.510 0.610386
## MainBreedLabrador Retriever 0.019 0.984874
## MainBreedLhasa Apso 0.607 0.543961
## MainBreedMaine Coon 0.759 0.448008
## MainBreedMaltese 0.476 0.634118
## MainBreedManchester Terrier 0.225 0.821872
## MainBreedManx 0.175 0.861337
## MainBreedMastiff -0.081 0.935682
## MainBreedMiniature Pinscher 0.099 0.921517
## MainBreedMixed Breed -0.502 0.615394
## MainBreedMountain Dog 0.000 1.000000
## MainBreedMunsterlander 0.352 0.724648
## MainBreedNebelung 0.000 0.999999
## MainBreedNorwegian Forest Cat 1.555 0.119968
## MainBreedOcicat 1.174 0.240253
## MainBreedOld English Sheepdog 0.000 1.000000
## MainBreedOrient Long Hair 1.289 0.197392
## MainBreedOrient Short Hair 0.145 0.884914
## MainBreedOrient Tabby -0.509 0.610748
## MainBreedPekingese 0.782 0.433933
## MainBreedPersian 1.171 0.241726
## MainBreedPit Bull Terrier -0.270 0.787304
## MainBreedPixie-Bob 0.000 1.000000
## MainBreedPomeranian 0.539 0.589767
## MainBreedPoodle 0.460 0.645554
## MainBreedPug 0.546 0.585280
## MainBreedRagdoll 1.500 0.133699
## MainBreedRetriever -0.114 0.909461
## MainBreedRhodesian Ridgeback 0.167 0.867694
## MainBreedRottweiler 0.341 0.733370
## MainBreedRussian Blue 1.139 0.254889
## MainBreedSaint Bernard 0.782 0.434426
## MainBreedSamoyed 0.000 1.000000
## MainBreedSchnauzer 0.269 0.788076
## MainBreedScottish Terrier Scottie 0.575 0.565629
## MainBreedSetter 0.000 0.999999
## MainBreedShar Pei 0.243 0.808256
## MainBreedShepherd -0.194 0.846158
## MainBreedShetland Sheepdog Sheltie 0.070 0.944197
## MainBreedShiba Inu -0.312 0.754994
## MainBreedShih Tzu 0.599 0.548881
## MainBreedSiamese 1.235 0.216924
## MainBreedSiberian Husky 0.337 0.736123
## MainBreedSilky Terrier 0.231 0.817058
## MainBreedSilver 0.000 0.999999
## MainBreedSingapura -0.570 0.568366
## MainBreedSnowshoe -0.320 0.748858
## MainBreedSomali 0.767 0.443002
## MainBreedSpaniel 0.000 1.000000
## MainBreedSphynx (hairless cat) 0.999 0.317811
## MainBreedSpitz -0.044 0.964602
## MainBreedStaffordshire Bull Terrier 0.000 1.000000
## MainBreedStandard Poodle -0.122 0.902982
## MainBreedTabby 0.891 0.372909
## MainBreedTerrier -0.344 0.730834
## MainBreedTiger 0.283 0.777395
## MainBreedTonkinese 0.931 0.351713
## MainBreedTorbie 1.397 0.162397
## MainBreedTortoiseshell 1.247 0.212291
## MainBreedToy Fox Terrier -0.341 0.732837
## MainBreedTurkish Angora 0.087 0.930953
## MainBreedTurkish Van -0.933 0.350854
## MainBreedTuxedo 0.357 0.721367
## MainBreedWeimaraner 0.000 0.999999
## MainBreedWelsh Corgi 0.906 0.365167
## MainBreedWest Highland White Terrier Westie 0.449 0.653718
## MainBreedWheaten Terrier 0.000 0.999999
## MainBreedWhite German Shepherd 0.074 0.941278
## MainBreedWirehaired Terrier 0.381 0.703453
## MainBreedYellow Labrador Retriever -1.004 0.315286
## MainBreedYorkshire Terrier Yorkie 0.858 0.391108
## has_name1 0.319 0.749403
## pure_breed1 NA NA
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for Negative Binomial(16669.18) family taken to be 1)
##
## Null deviance: 7298.9 on 10503 degrees of freedom
## Residual deviance: 6757.7 on 10323 degrees of freedom
## (2754 observations deleted due to missingness)
## AIC: 17566
##
## Number of Fisher Scoring iterations: 1
##
##
## Theta: 16669
## Std. Err.: 22000
## Warning while fitting theta: alternation limit reached
##
## 2 x log-likelihood: -17202.01Negative binomial model with significant variables:
modelnegb2 <- glm.nb(High~ Age + FurLength + Health+
as.factor(Gender) +
as.factor(Vaccinated) +
as.factor(Sterilized)+
as.factor(Color1), data = train1)
summary(modelnegb2)##
## Call:
## glm.nb(formula = High ~ Age + FurLength + Health + as.factor(Gender) +
## as.factor(Vaccinated) + as.factor(Sterilized) + as.factor(Color1),
## data = train1, init.theta = 17299.81994, link = log)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -1.3463 -0.9836 -0.6856 0.5725 1.3332
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -1.037513 0.096130 -10.793 < 2e-16 ***
## Age -0.003208 0.000995 -3.225 0.001262 **
## FurLength 0.134519 0.022733 5.917 3.27e-09 ***
## Health -0.138554 0.075953 -1.824 0.068120 .
## as.factor(Gender)2 -0.128883 0.030167 -4.272 1.93e-05 ***
## as.factor(Gender)3 -0.219131 0.044147 -4.964 6.92e-07 ***
## as.factor(Vaccinated)2 0.132879 0.033827 3.928 8.56e-05 ***
## as.factor(Vaccinated)3 0.028352 0.054183 0.523 0.600794
## as.factor(Sterilized)2 0.414381 0.045838 9.040 < 2e-16 ***
## as.factor(Sterilized)3 0.228526 0.064635 3.536 0.000407 ***
## as.factor(Color1)2 -0.037595 0.034951 -1.076 0.282089
## as.factor(Color1)3 0.083682 0.057252 1.462 0.143843
## as.factor(Color1)4 -0.131694 0.073257 -1.798 0.072223 .
## as.factor(Color1)5 0.100691 0.058370 1.725 0.084520 .
## as.factor(Color1)6 0.133284 0.065103 2.047 0.040630 *
## as.factor(Color1)7 0.104872 0.065793 1.594 0.110941
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for Negative Binomial(17299.82) family taken to be 1)
##
## Null deviance: 7302.9 on 10507 degrees of freedom
## Residual deviance: 6997.5 on 10492 degrees of freedom
## (2750 observations deleted due to missingness)
## AIC: 17476
##
## Number of Fisher Scoring iterations: 1
##
##
## Theta: 17300
## Std. Err.: 23665
## Warning while fitting theta: iteration limit reached
##
## 2 x log-likelihood: -17441.78modelnegb3 <- glm.nb(High~ Age + FurLength + Health+
as.factor(Gender) +
as.factor(Color1), data = train1)
summary(modelnegb3)##
## Call:
## glm.nb(formula = High ~ Age + FurLength + Health + as.factor(Gender) +
## as.factor(Color1), data = train1, init.theta = 17830.91647,
## link = log)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -1.2875 -0.9753 -0.6593 0.6000 1.5675
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -0.6132553 0.0881599 -6.956 3.50e-12 ***
## Age -0.0082888 0.0009764 -8.489 < 2e-16 ***
## FurLength 0.1417395 0.0226634 6.254 4.00e-10 ***
## Health -0.1189043 0.0753947 -1.577 0.1148
## as.factor(Gender)2 -0.1515801 0.0300709 -5.041 4.64e-07 ***
## as.factor(Gender)3 -0.1845937 0.0436871 -4.225 2.39e-05 ***
## as.factor(Color1)2 -0.0520582 0.0348861 -1.492 0.1356
## as.factor(Color1)3 0.0815006 0.0572268 1.424 0.1544
## as.factor(Color1)4 -0.1325599 0.0732325 -1.810 0.0703 .
## as.factor(Color1)5 0.0740500 0.0582930 1.270 0.2040
## as.factor(Color1)6 0.1357831 0.0650674 2.087 0.0369 *
## as.factor(Color1)7 0.0829134 0.0657301 1.261 0.2072
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for Negative Binomial(17830.92) family taken to be 1)
##
## Null deviance: 7302.9 on 10507 degrees of freedom
## Residual deviance: 7146.6 on 10496 degrees of freedom
## (2750 observations deleted due to missingness)
## AIC: 17617
##
## Number of Fisher Scoring iterations: 1
##
##
## Theta: 17831
## Std. Err.: 25059
## Warning while fitting theta: iteration limit reached
##
## 2 x log-likelihood: -17590.93Linear model with significant variables:
modellin <- lm(High~ Age + FurLength + Health+
as.factor(Gender) +
as.factor(Vaccinated) +
as.factor(Sterilized)+
as.factor(Color1), data = train1)
summary(modellin)##
## Call:
## lm(formula = High ~ Age + FurLength + Health + as.factor(Gender) +
## as.factor(Vaccinated) + as.factor(Sterilized) + as.factor(Color1),
## data = train1)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.8089 -0.4918 -0.1805 0.4622 0.9506
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.355997 0.030261 11.764 < 2e-16 ***
## Age -0.001322 0.000292 -4.529 5.98e-06 ***
## FurLength 0.067127 0.007984 8.408 < 2e-16 ***
## Health -0.062218 0.023716 -2.623 0.00872 **
## as.factor(Gender)2 -0.064853 0.010469 -6.194 6.07e-10 ***
## as.factor(Gender)3 -0.110770 0.015056 -7.357 2.02e-13 ***
## as.factor(Vaccinated)2 0.069331 0.011689 5.931 3.10e-09 ***
## as.factor(Vaccinated)3 0.013287 0.017927 0.741 0.45861
## as.factor(Sterilized)2 0.176341 0.013875 12.709 < 2e-16 ***
## as.factor(Sterilized)3 0.085058 0.020099 4.232 2.34e-05 ***
## as.factor(Color1)2 -0.017676 0.011732 -1.507 0.13192
## as.factor(Color1)3 0.042561 0.020381 2.088 0.03679 *
## as.factor(Color1)4 -0.061837 0.023855 -2.592 0.00955 **
## as.factor(Color1)5 0.049674 0.020664 2.404 0.01624 *
## as.factor(Color1)6 0.070713 0.023644 2.991 0.00279 **
## as.factor(Color1)7 0.053539 0.023383 2.290 0.02206 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.4864 on 10492 degrees of freedom
## (2750 observations deleted due to missingness)
## Multiple R-squared: 0.05498, Adjusted R-squared: 0.05363
## F-statistic: 40.7 on 15 and 10492 DF, p-value: < 2.2e-16library(kableExtra)
aic1 <- modelnegb$aic
aic2 <- modelnegb1$aic
aic3 <- modelnegb2$aic
aic4 <- modellin$aic
mse1 <- mean((train1$High - predict(modelnegb))^2)
mse2 <- mean((train1$High - predict(modelnegb1))^2)
mse3 <- mean((train1$High - predict(modelnegb2))^2)
mse4 <- mean((train1$High - predict(modellin))^2)
compare_aic_mse <- matrix(c(mse1, mse2, mse3 ,mse4 ,aic1, aic2,aic3,aic4),nrow=4,ncol=2,byrow=TRUE)
rownames(compare_aic_mse) <- c("Model1","Model2","Model3","Model4")
colnames(compare_aic_mse) <- c("MSE","AIC")
compare_models <- as.data.frame(compare_models)
kable(compare_aic_mse) %>%
kable_styling(full_width = T)| MSE | AIC | |
|---|---|---|
| Model1 | NA | NA |
| Model2 | NA | NA |
| Model3 | 19990.89 | 17566.01 |
| Model4 | 17475.78 | NA |
The negative binomial model with significant variables and lower AIC score is selected:
We are going to deploy this model on our test data.
pred <- predict(modelnegb2, train1, type = "response")
summary(pred)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.1813 0.4076 0.5103 0.4952 0.5852 0.9092pred1 <- predict(modellin, train1, type = "response")
summary(pred1)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.04944 0.42064 0.51851 0.49535 0.58721 0.81022