library(data.table) #reading in the data
library(dplyr) #dataframe manipulation
library(ggplot2) #viz
library(ranger) #the random forest implementation
library(plotly) #3D plotting
library(tidyr) #dataframe manipulation
library(FNN) #k nearest neighbors algorithm
library(xgboost)

fb <- fread("../input/train.csv", integer64 = "character", showProgress = FALSE)


fb %>% filter(x >1, x <1.25, y >2.5, y < 2.75) -> fb
head(fb, 3)


fb$hour = (fb$time/60) %% 24
fb$weekday = (fb$time/(60*24)) %% 7
fb$month = (fb$time/(60*24*30)) %% 12 #month-ish
fb$year = fb$time/(60*24*365)
fb$day = fb$time/(60*24) %% 365


small_train = fb[fb$time < 7.3e5,]
small_val = fb[fb$time >= 7.3e5,] 



### Exploratory Analysis:
ggplot(small_train, aes(x, y )) +
    geom_point(aes(color = place_id)) + 
    theme_minimal() +
    theme(legend.position = "none") +
    ggtitle("Check-ins colored by place_id")
small_train %>% count(place_id) %>% filter(n > 500) -> ids
small_trainz = small_train[small_train$place_id %in% ids$place_id,]

plot_ly(data = small_trainz, x = x , y = y, z = hour, color = place_id,  type = "scatter3d", mode = "markers", marker=list(size= 5)) %>% layout(title = "Place_id's by position and Time of Day")
plot_ly(data = small_trainz, x = x , y = y, z = weekday, color = place_id,  type = "scatter3d", mode = "markers", marker=list(size= 5)) %>% layout(title = "Place_id's by position and Day of Week")

length(unique(small_train$place_id))
small_train %>% count(place_id) %>% filter(n > 3) -> ids
small_train = small_train[small_train$place_id %in% ids$place_id,]
### K Nearest Neighbors
s = 2
l = 125
w = 500

create_matrix = function(train) {
    cbind(s*train$y,
          train$x,
          train$hour/l,
          train$weekday/w,
          train$year/w,
          train$month/w,
          train$time/(w*60*24*7))
    }

X = create_matrix(small_train)
X_val = create_matrix(small_val)

model_knn = FNN::knn(train = X, test = X_val, cl = small_train$place_id, k = 15)

preds <- as.character(model_knn)
truth <- as.character(small_val$place_id)
mean(truth == preds)

### The Forest:
set.seed(131L)
small_train$place_id <- as.factor(small_train$place_id) # ranger needs factors for classification
model_rf <- ranger(place_id ~ x + y + accuracy + hour + weekday + month + year,
                   small_train,
                   num.trees = 100,
                   write.forest = TRUE,
                   importance = "impurity")


pred = predict(model_rf, small_val)
pred = pred$predictions
accuracy = mean(pred == small_val$place_id) 
small_val$Correct = (pred == small_val$place_id)

ggplot(small_val, aes(x, y )) +
    geom_point(aes(color = Correct)) + 
    theme_minimal() +
    scale_color_brewer(palette = "Set1")
#reordering the levels based on counts:
small_val$place_id <- factor(small_val$place_id,
                             levels = names(sort(table(small_val$place_id), decreasing = TRUE)))

small_val %>% 
    ggplot(aes(x = place_id)) + geom_bar(aes(fill = Correct)) + 
    theme_minimal() +
    theme(axis.text.x = element_blank()) +
    ggtitle("Prediction Accuracy by ID and Popularity") +
    scale_fill_brewer(palette = "Set1")
data.frame(as.list(model_rf$variable.importance)) %>% gather() %>% 
    ggplot(aes(x = reorder(key, value), y = value)) +
    geom_bar(stat = "identity", width = 0.6, fill = "grey") +
    coord_flip() +
    theme_minimal() +
    ggtitle("Variable Importance (Gini Index)") +
    theme(axis.title.y = element_blank())