SEMOGA-FIX.R

library(reticulate)

## Warning: package 'reticulate' was built under R version 4.5.2

Sys.setenv(RETICULATE_PYTHON = "C:/Users/ASUS/miniforge3/envs/env_skripsi/python.exe")
py_discover_config()

## python:         C:/Users/ASUS/miniforge3/envs/env_skripsi/python.exe
## libpython:      C:/Users/ASUS/miniforge3/envs/env_skripsi/python310.dll
## pythonhome:     C:/Users/ASUS/miniforge3/envs/env_skripsi
## version:        3.10.20 | packaged by conda-forge | (main, Mar  5 2026, 16:36:49) [MSC v.1944 64 bit (AMD64)]
## Architecture:   64bit
## numpy:          C:/Users/ASUS/miniforge3/envs/env_skripsi/Lib/site-packages/numpy
## numpy_version:  2.2.6
## 
## NOTE: Python version was forced by RETICULATE_PYTHON

Sys.setenv(RETICULATE_PYTHON = "C:/Users/ASUS/miniforge3/envs/env_skripsi/python.exe")
library(keras)

## Warning: package 'keras' was built under R version 4.5.3

## The keras package is deprecated. Please use the keras3 package instead.
## Alternatively, to continue using legacy keras, call `py_require_legacy_keras()`.

library(tensorflow)

## Warning: package 'tensorflow' was built under R version 4.5.3

# =========================
# LIBRARY
# =========================
library(tm)

## Warning: package 'tm' was built under R version 4.5.2

## Loading required package: NLP

library(wordcloud)

## Loading required package: RColorBrewer

library(RColorBrewer)
library(readr)
library(tidyverse)

## Warning: package 'tidyverse' was built under R version 4.5.3

## Warning: package 'lubridate' was built under R version 4.5.2

## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.4     ✔ purrr     1.0.4
## ✔ forcats   1.0.1     ✔ stringr   1.5.1
## ✔ ggplot2   3.5.2     ✔ tibble    3.3.0
## ✔ lubridate 1.9.5     ✔ tidyr     1.3.1

## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ ggplot2::annotate() masks NLP::annotate()
## ✖ dplyr::filter()     masks stats::filter()
## ✖ dplyr::lag()        masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors

library(tidytext)

## Warning: package 'tidytext' was built under R version 4.5.3

library(textclean)

## Warning: package 'textclean' was built under R version 4.5.3

library(dplyr)
library(stringr)
library(stopwords)

## Warning: package 'stopwords' was built under R version 4.5.2

## 
## Attaching package: 'stopwords'
## 
## The following object is masked from 'package:tm':
## 
##     stopwords

library(caret)

## Warning: package 'caret' was built under R version 4.5.3

## Loading required package: lattice
## 
## Attaching package: 'caret'
## 
## The following object is masked from 'package:purrr':
## 
##     lift
## 
## The following object is masked from 'package:tensorflow':
## 
##     train

library(ggplot2)
library(SnowballC)

## Warning: package 'SnowballC' was built under R version 4.5.2

library(wordcloud2)

## Warning: package 'wordcloud2' was built under R version 4.5.3

# =========================
# INPUT DATA
# =========================
setwd("~/Desktop/RISET DAN KAJIAN STRATEGIS")

df <- read.csv("datariset.csv", sep = ";",
               fileEncoding = "latin1",
               stringsAsFactors = FALSE)

df$doc_id <- 1:nrow(df)

# =========================
# STOPWORDS
# =========================
stopword <- c(
  "aku", "saya", "gue", "gw", "gua", "ane", "kita", "kami", "kamu", "lu", "lo", "loe",
  "kalian", "kau", "dia", "mereka", "beliau", "kelen", "kak", "bang", "bro", "sis", "dek",
  "pak", "ibu", "bu", "mas", "om", "tante", "bapak", "bapaknya", "bg", "ka", "ini", "itu",
  "sini", "situ", "sana", "di", "ke", "dari", "pada", "dalam", "luar", "atas", "bawah",
  "tengah", "depan", "belakang", "antara", "t4", "dan", "atau", "tapi", "tetapi", "namun",
  "karena", "karna", "sebab", "sehingga", "supaya", "agar", "maka", "jika", "kalau", "kalo",
  "klo", "bila", "apabila", "bahwa", "walaupun", "meskipun", "padahal", "sedangkan",
  "ketika", "saat", "waktu", "setelah", "sebelum", "selama", "sejak", "hingga", "sampai",
  "sampe", "serta", "maupun", "untuk", "buat", "dengan", "tanpa", "oleh", "tentang",
  "mengenai", "terhadap", "kepada", "bagi", "per", "secara", "seperti", "sebagai",
  "berdasarkan", "sudah", "udah", "udh", "belum", "blm", "blum", "masih", "lagi", "terus",
  "trus", "selalu", "sering", "kadang", "pernah", "tidak", "gak", "ga", "gk", "ngga",
  "nggak", "enggak", "tak", "bukan", "bkn", "jangan", "harus", "wajib", "pasti", "mungkin",
  "hampir", "sangat", "banget", "bgt", "sekali", "amat", "terlalu", "cukup", "hanya", "saja",
  "aja", "cuma", "cuman", "doang", "juga", "jg", "pun", "lah", "loh", "deh", "nih", "tuh",
  "sih", "dong", "kan", "kah", "pula", "bahkan", "malah", "justru", "emang", "memang",
  "emng", "emg", "lagian", "sebenarnya", "sebenernya", "seharusnya", "harusnya", "sekarang",
  "skrg", "dulu", "nanti", "kini", "tadi", "besok", "kemarin", "bisa", "dapat", "boleh",
  "mau", "akan", "ingin", "minta", "perlu", "sempat", "langsung", "apa", "siapa", "mana",
  "dimana", "kemana", "kenapa", "mengapa", "kapan", "bagaimana", "gimana", "berapa", "ada",
  "banyak", "semua", "beberapa", "setiap", "tiap", "lain", "lainnya", "satu", "dua", "tiga",
  "sama", "beda", "sendiri", "begini", "begitu", "gini", "gitu", "gtu", "kayak", "kaya",
  "kek", "ibaratnya", "contoh", "misalnya", "jelas", "jadi", "jd", "jdi", "hal", "cara",
  "wkwk", "wkwkwk", "wkwkwkw", "wkwkwkwk", "wkwkw", "haha", "hehe", "hihi", "hahaha", "lol",
  "hah", "heh", "nah", "yah", "yaah", "wah", "wow", "aduh", "duh", "eh", "ih", "ah", "oh",
  "hayoloh", "hadeh", "haduuh", "haduh", "lha", "lho", "woi", "oi", "hai", "hei", "halo",
  "hey", "waduh", "astagfirullah", "astaghfirullah", "masya", "subhanallah", "alhamdulillah",
  "aamiin", "amiin", "ya", "iya", "iyaa", "yap", "yep", "oke", "ok", "oks", "nope", "sip",
  "siap", "baik", "betul", "bener", "beneran", "benar", "setuju", "iyalah", "dah", "yg",
  "yng", "dgn", "utk", "tdk", "sdh", "blm", "krn", "kpd", "tsb", "dst", "dll", "dsb", "jg",
  "tp", "tpi", "bs", "lg", "sm", "skrg", "org", "bnyk", "bgt", "udh", "emg", "gk", "gak",
  "klo", "klu", "jd", "jdi", "tu", "ni", "dg", "d", "k", "ny", "msh", "min", "mimin", "bos",
  "orang", "tempat", "hari", "tahun", "bulan", "jam", "menit", "kali", "masalah", "situasi",
  "kondisi", "urusan", "info", "berita", "video", "konten", "postingan", "status", "jadi",
  "berarti", "makanya", "soalnya", "soal", "intinya", "pokoknya", "maksudnya", "artinya",
  "katanya", "bilangnya", "konon", "kabarnya", "ceritanya", "setuju", "sependapat",
  "sepakat", "lanjut", "skip", "bye", "selamat", "thanks", "makasih", "terima", "kasih",
  "noted","yang","yg","kata","bikin","lihat","liat","bikin","makan","biasa","pake","kena","salah","jual","masuk","bodoh","tolol","dongo","smpe","maaf","asli","manusia","endara","para","goblok","allah","Allah","ALLAH","lebih","cari","kasih",""
)

# =========================
# PREPROCESSING
# =========================
df <- df %>%
  mutate(
    text_clean = text %>%
      tolower() %>%
      replace_url() %>%
      replace_html() %>%
      gsub("@\\w+", "", .) %>%
      gsub("#\\w+", "", .) %>%
      gsub("[^a-z ]", " ", .) %>%
      gsub("\\s+", " ", .) %>%
      trimws()
  )

df_token_clean <- df %>%
  unnest_tokens(kata, text_clean) %>%
  filter(!kata %in% stopword) %>%
  filter(nchar(kata) > 3) %>%
  mutate(kata = wordStem(kata, language = "indonesian"))

df_text_bersih <- df_token_clean %>%
  group_by(doc_id) %>%
  summarise(text_clean = paste(kata, collapse = " "))

df <- df %>%
  select(-text_clean) %>%
  left_join(df_text_bersih, by = "doc_id") %>%
  filter(text_clean != "")

# =========================
# LABELING
# =========================
kata_positif <- read.csv("C:/Users/ASUS/Downloads/positive.tsv", sep = "\t",
                         col.names = c("kata","bobot")) %>%
  mutate(bobot = as.numeric(bobot)) %>%
  filter(!is.na(bobot))

kata_negatif <- read.csv("C:/Users/ASUS/Downloads/negative.tsv", sep = "\t",
                         col.names = c("kata","bobot")) %>%
  mutate(bobot = as.numeric(bobot)) %>%
  filter(!is.na(bobot))

kamus <- bind_rows(kata_positif, kata_negatif)

df <- df %>% mutate(id_baris = row_number())

df_token <- df %>% unnest_tokens(kata, text_clean)

df_skor <- df_token %>%
  inner_join(kamus, by = "kata") %>%
  group_by(id_baris) %>%
  summarise(total_skor = sum(bobot, na.rm = TRUE))

## Warning in inner_join(., kamus, by = "kata"): Detected an unexpected many-to-many relationship between `x` and `y`.
## ℹ Row 2 of `x` matches multiple rows in `y`.
## ℹ Row 5458 of `y` matches multiple rows in `x`.
## ℹ If a many-to-many relationship is expected, set `relationship =
##   "many-to-many"` to silence this warning.

df_final <- df %>%
  left_join(df_skor, by = "id_baris") %>%
  mutate(
    total_skor = replace_na(total_skor, 0),
    label = case_when(
      total_skor > 0 ~ "Positif",
      total_skor < 0 ~ "Negatif",
      TRUE ~ "Netral"
    )
  )

# =========================
# TOKENIZER
# =========================
max_words <- as.integer(5000)
max_len   <- as.integer(50)

tokenizer <- text_tokenizer(num_words = max_words)
tokenizer %>% fit_text_tokenizer(df_final$text_clean)

x_data <- texts_to_sequences(tokenizer, df_final$text_clean) %>%
  pad_sequences(maxlen = max_len)

label_index <- df_final$label %>%
  factor(levels = c("Negatif","Netral","Positif")) %>%
  as.integer() - 1

# =========================
# ONE HOT
# =========================
num_classes <- as.integer(3)

y_data <- matrix(0, nrow = length(label_index), ncol = num_classes)
for(i in 1:length(label_index)) {
  y_data[i, label_index[i] + 1] <- 1
}

# =========================
# NUMPY
# =========================
np <- import("numpy")
x_data <- np$array(x_data, dtype = "int32")
y_data <- np$array(y_data, dtype = "float32")

# =========================
# SPLIT DATA
# =========================
set.seed(123)
n <- nrow(x_data)
train_index <- sample(1:n, 0.8 * n)

x_train <- x_data[train_index, ]
x_test  <- x_data[-train_index, ]

y_train <- y_data[train_index, ]
y_test  <- y_data[-train_index, ]

# =========================
# MODEL BI-LSTM
# =========================
model <- keras_model_sequential()

model$add(layer_embedding(
  input_dim = as.integer(max_words),
  output_dim = as.integer(128),
  input_length = as.integer(max_len)
))

model$add(keras$layers$Bidirectional(
  layer_lstm(
    units = as.integer(64),
    return_sequences = TRUE,
    dropout = 0.2
  )
))

model$add(layer_lstm(units = as.integer(32)))

model$add(layer_dense(units = as.integer(32), activation = "relu"))

model$add(layer_dropout(rate = 0.5)) 

model$add(layer_dense(units = as.integer(num_classes), activation = "softmax"))

model$build(input_shape = tuple(NULL, max_len))

model$compile(
  loss = "categorical_crossentropy",
  optimizer = "adam",
  metrics = list("accuracy")
)

model$summary()

## Model: "sequential"
## ┌─────────────────────────────────┬────────────────────────┬───────────────┐
## │ Layer (type)                    │ Output Shape           │       Param # │
## ├─────────────────────────────────┼────────────────────────┼───────────────┤
## │ embedding (Embedding)           │ (None, 50, 128)        │       640,000 │
## ├─────────────────────────────────┼────────────────────────┼───────────────┤
## │ bidirectional (Bidirectional)   │ (None, 50, 128)        │        98,816 │
## ├─────────────────────────────────┼────────────────────────┼───────────────┤
## │ lstm_1 (LSTM)                   │ (None, 32)             │        20,608 │
## ├─────────────────────────────────┼────────────────────────┼───────────────┤
## │ dense (Dense)                   │ (None, 32)             │         1,056 │
## ├─────────────────────────────────┼────────────────────────┼───────────────┤
## │ dropout (Dropout)               │ (None, 32)             │             0 │
## ├─────────────────────────────────┼────────────────────────┼───────────────┤
## │ dense_1 (Dense)                 │ (None, 3)              │            99 │
## └─────────────────────────────────┴────────────────────────┴───────────────┘
##  Total params: 760,579 (2.90 MB)
##  Trainable params: 760,579 (2.90 MB)
##  Non-trainable params: 0 (0.00 B)

# =========================
# CALLBACK
# =========================
early_stop <- callback_early_stopping(
  monitor = "val_loss",
  patience = as.integer(3),
  restore_best_weights = TRUE
)

# =========================
# TRAINING 
# =========================
history <- model$fit(
  x_train,
  y_train,
  epochs = as.integer(10),
  batch_size = as.integer(32),
  validation_split = 0.2,
  callbacks = list(early_stop)
)

## Epoch 1/10
## 
##  1/65 ━━━━━━━━━━━━━━━━━━━━ 13:58 13s/step - accuracy: 0.2500 - loss: 1.1018
##  2/65 ━━━━━━━━━━━━━━━━━━━━ 23s 372ms/step - accuracy: 0.3203 - loss: 1.0979
##  3/65 ━━━━━━━━━━━━━━━━━━━━ 22s 356ms/step - accuracy: 0.3524 - loss: 1.0949
##  4/65 ━━━━━━━━━━━━━━━━━━━━ 21s 357ms/step - accuracy: 0.3717 - loss: 1.0945
##  5/65 ━━━━━━━━━━━━━━━━━━━━ 21s 361ms/step - accuracy: 0.3849 - loss: 1.0931
##  6/65 ━━━━━━━━━━━━━━━━━━━━ 20s 354ms/step - accuracy: 0.3937 - loss: 1.0915
##  7/65 ━━━━━━━━━━━━━━━━━━━━ 20s 352ms/step - accuracy: 0.4025 - loss: 1.0891
##  8/65 ━━━━━━━━━━━━━━━━━━━━ 20s 352ms/step - accuracy: 0.4064 - loss: 1.0883
##  9/65 ━━━━━━━━━━━━━━━━━━━━ 19s 356ms/step - accuracy: 0.4102 - loss: 1.0872
## 10/65 ━━━━━━━━━━━━━━━━━━━━ 19s 356ms/step - accuracy: 0.4139 - loss: 1.0865
## 11/65 ━━━━━━━━━━━━━━━━━━━━ 19s 354ms/step - accuracy: 0.4155 - loss: 1.0861
## 12/65 ━━━━━━━━━━━━━━━━━━━━ 18s 351ms/step - accuracy: 0.4169 - loss: 1.0854
## 13/65 ━━━━━━━━━━━━━━━━━━━━ 18s 349ms/step - accuracy: 0.4178 - loss: 1.0848
## 14/65 ━━━━━━━━━━━━━━━━━━━━ 17s 347ms/step - accuracy: 0.4193 - loss: 1.0838
## 15/65 ━━━━━━━━━━━━━━━━━━━━ 17s 352ms/step - accuracy: 0.4204 - loss: 1.0831
## 16/65 ━━━━━━━━━━━━━━━━━━━━ 17s 353ms/step - accuracy: 0.4210 - loss: 1.0823
## 17/65 ━━━━━━━━━━━━━━━━━━━━ 17s 355ms/step - accuracy: 0.4218 - loss: 1.0817
## 18/65 ━━━━━━━━━━━━━━━━━━━━ 16s 353ms/step - accuracy: 0.4227 - loss: 1.0808
## 19/65 ━━━━━━━━━━━━━━━━━━━━ 16s 353ms/step - accuracy: 0.4235 - loss: 1.0801
## 20/65 ━━━━━━━━━━━━━━━━━━━━ 15s 355ms/step - accuracy: 0.4246 - loss: 1.0792
## 21/65 ━━━━━━━━━━━━━━━━━━━━ 15s 353ms/step - accuracy: 0.4258 - loss: 1.0782
## 22/65 ━━━━━━━━━━━━━━━━━━━━ 15s 352ms/step - accuracy: 0.4271 - loss: 1.0770
## 23/65 ━━━━━━━━━━━━━━━━━━━━ 14s 352ms/step - accuracy: 0.4285 - loss: 1.0760
## 24/65 ━━━━━━━━━━━━━━━━━━━━ 14s 353ms/step - accuracy: 0.4302 - loss: 1.0749
## 25/65 ━━━━━━━━━━━━━━━━━━━━ 14s 353ms/step - accuracy: 0.4317 - loss: 1.0739
## 26/65 ━━━━━━━━━━━━━━━━━━━━ 13s 352ms/step - accuracy: 0.4332 - loss: 1.0728
## 27/65 ━━━━━━━━━━━━━━━━━━━━ 13s 351ms/step - accuracy: 0.4346 - loss: 1.0718
## 28/65 ━━━━━━━━━━━━━━━━━━━━ 12s 350ms/step - accuracy: 0.4359 - loss: 1.0707
## 29/65 ━━━━━━━━━━━━━━━━━━━━ 12s 349ms/step - accuracy: 0.4373 - loss: 1.0697
## 30/65 ━━━━━━━━━━━━━━━━━━━━ 12s 347ms/step - accuracy: 0.4384 - loss: 1.0688
## 31/65 ━━━━━━━━━━━━━━━━━━━━ 12s 380ms/step - accuracy: 0.4394 - loss: 1.0680
## 32/65 ━━━━━━━━━━━━━━━━━━━━ 12s 380ms/step - accuracy: 0.4404 - loss: 1.0673
## 33/65 ━━━━━━━━━━━━━━━━━━━━ 12s 386ms/step - accuracy: 0.4412 - loss: 1.0668
## 34/65 ━━━━━━━━━━━━━━━━━━━━ 11s 385ms/step - accuracy: 0.4420 - loss: 1.0663
## 35/65 ━━━━━━━━━━━━━━━━━━━━ 11s 385ms/step - accuracy: 0.4426 - loss: 1.0659
## 36/65 ━━━━━━━━━━━━━━━━━━━━ 11s 387ms/step - accuracy: 0.4433 - loss: 1.0654
## 37/65 ━━━━━━━━━━━━━━━━━━━━ 10s 386ms/step - accuracy: 0.4440 - loss: 1.0649
## 38/65 ━━━━━━━━━━━━━━━━━━━━ 10s 386ms/step - accuracy: 0.4447 - loss: 1.0644
## 39/65 ━━━━━━━━━━━━━━━━━━━━ 9s 380ms/step - accuracy: 0.4454 - loss: 1.0640 
## 40/65 ━━━━━━━━━━━━━━━━━━━━ 9s 375ms/step - accuracy: 0.4462 - loss: 1.0635
## 41/65 ━━━━━━━━━━━━━━━━━━━━ 8s 370ms/step - accuracy: 0.4470 - loss: 1.0630
## 42/65 ━━━━━━━━━━━━━━━━━━━━ 8s 371ms/step - accuracy: 0.4478 - loss: 1.0626
## 43/65 ━━━━━━━━━━━━━━━━━━━━ 8s 375ms/step - accuracy: 0.4486 - loss: 1.0621
## 44/65 ━━━━━━━━━━━━━━━━━━━━ 7s 375ms/step - accuracy: 0.4495 - loss: 1.0617
## 45/65 ━━━━━━━━━━━━━━━━━━━━ 7s 376ms/step - accuracy: 0.4503 - loss: 1.0612
## 46/65 ━━━━━━━━━━━━━━━━━━━━ 7s 378ms/step - accuracy: 0.4511 - loss: 1.0607
## 47/65 ━━━━━━━━━━━━━━━━━━━━ 6s 378ms/step - accuracy: 0.4520 - loss: 1.0602
## 48/65 ━━━━━━━━━━━━━━━━━━━━ 6s 380ms/step - accuracy: 0.4528 - loss: 1.0597
## 49/65 ━━━━━━━━━━━━━━━━━━━━ 6s 383ms/step - accuracy: 0.4536 - loss: 1.0592
## 50/65 ━━━━━━━━━━━━━━━━━━━━ 5s 385ms/step - accuracy: 0.4544 - loss: 1.0587
## 51/65 ━━━━━━━━━━━━━━━━━━━━ 5s 386ms/step - accuracy: 0.4551 - loss: 1.0582
## 52/65 ━━━━━━━━━━━━━━━━━━━━ 5s 389ms/step - accuracy: 0.4558 - loss: 1.0576
## 53/65 ━━━━━━━━━━━━━━━━━━━━ 4s 392ms/step - accuracy: 0.4566 - loss: 1.0571
## 54/65 ━━━━━━━━━━━━━━━━━━━━ 4s 393ms/step - accuracy: 0.4573 - loss: 1.0565
## 55/65 ━━━━━━━━━━━━━━━━━━━━ 3s 394ms/step - accuracy: 0.4580 - loss: 1.0559
## 56/65 ━━━━━━━━━━━━━━━━━━━━ 3s 395ms/step - accuracy: 0.4588 - loss: 1.0554
## 57/65 ━━━━━━━━━━━━━━━━━━━━ 3s 395ms/step - accuracy: 0.4595 - loss: 1.0548
## 58/65 ━━━━━━━━━━━━━━━━━━━━ 2s 396ms/step - accuracy: 0.4603 - loss: 1.0541
## 59/65 ━━━━━━━━━━━━━━━━━━━━ 2s 397ms/step - accuracy: 0.4611 - loss: 1.0535
## 60/65 ━━━━━━━━━━━━━━━━━━━━ 1s 397ms/step - accuracy: 0.4618 - loss: 1.0529
## 61/65 ━━━━━━━━━━━━━━━━━━━━ 1s 398ms/step - accuracy: 0.4626 - loss: 1.0522
## 62/65 ━━━━━━━━━━━━━━━━━━━━ 1s 398ms/step - accuracy: 0.4633 - loss: 1.0516
## 63/65 ━━━━━━━━━━━━━━━━━━━━ 0s 400ms/step - accuracy: 0.4641 - loss: 1.0510
## 64/65 ━━━━━━━━━━━━━━━━━━━━ 0s 401ms/step - accuracy: 0.4648 - loss: 1.0504
## 65/65 ━━━━━━━━━━━━━━━━━━━━ 0s 425ms/step - accuracy: 0.4655 - loss: 1.0499
## 65/65 ━━━━━━━━━━━━━━━━━━━━ 46s 522ms/step - accuracy: 0.5110 - loss: 1.0137 - val_accuracy: 0.5984 - val_loss: 0.8940
## Epoch 2/10
## 
##  1/65 ━━━━━━━━━━━━━━━━━━━━ 8:04 8s/step - accuracy: 0.5625 - loss: 0.9500
##  2/65 ━━━━━━━━━━━━━━━━━━━━ 25s 403ms/step - accuracy: 0.5703 - loss: 0.9253
##  3/65 ━━━━━━━━━━━━━━━━━━━━ 23s 376ms/step - accuracy: 0.5677 - loss: 0.9314
##  4/65 ━━━━━━━━━━━━━━━━━━━━ 23s 390ms/step - accuracy: 0.5605 - loss: 0.9371
##  5/65 ━━━━━━━━━━━━━━━━━━━━ 23s 393ms/step - accuracy: 0.5572 - loss: 0.9422
##  6/65 ━━━━━━━━━━━━━━━━━━━━ 22s 381ms/step - accuracy: 0.5581 - loss: 0.9446
##  7/65 ━━━━━━━━━━━━━━━━━━━━ 21s 367ms/step - accuracy: 0.5593 - loss: 0.9457
##  8/65 ━━━━━━━━━━━━━━━━━━━━ 20s 366ms/step - accuracy: 0.5588 - loss: 0.9471
##  9/65 ━━━━━━━━━━━━━━━━━━━━ 20s 366ms/step - accuracy: 0.5592 - loss: 0.9478
## 10/65 ━━━━━━━━━━━━━━━━━━━━ 20s 370ms/step - accuracy: 0.5601 - loss: 0.9471
## 11/65 ━━━━━━━━━━━━━━━━━━━━ 20s 376ms/step - accuracy: 0.5609 - loss: 0.9465
## 12/65 ━━━━━━━━━━━━━━━━━━━━ 19s 374ms/step - accuracy: 0.5619 - loss: 0.9456
## 13/65 ━━━━━━━━━━━━━━━━━━━━ 19s 370ms/step - accuracy: 0.5641 - loss: 0.9434
## 14/65 ━━━━━━━━━━━━━━━━━━━━ 18s 367ms/step - accuracy: 0.5663 - loss: 0.9413
## 15/65 ━━━━━━━━━━━━━━━━━━━━ 18s 364ms/step - accuracy: 0.5679 - loss: 0.9400
## 16/65 ━━━━━━━━━━━━━━━━━━━━ 17s 363ms/step - accuracy: 0.5696 - loss: 0.9390
## 17/65 ━━━━━━━━━━━━━━━━━━━━ 17s 368ms/step - accuracy: 0.5716 - loss: 0.9374
## 18/65 ━━━━━━━━━━━━━━━━━━━━ 17s 368ms/step - accuracy: 0.5733 - loss: 0.9358
## 19/65 ━━━━━━━━━━━━━━━━━━━━ 16s 368ms/step - accuracy: 0.5748 - loss: 0.9348
## 20/65 ━━━━━━━━━━━━━━━━━━━━ 16s 371ms/step - accuracy: 0.5764 - loss: 0.9335
## 21/65 ━━━━━━━━━━━━━━━━━━━━ 16s 372ms/step - accuracy: 0.5782 - loss: 0.9322
## 22/65 ━━━━━━━━━━━━━━━━━━━━ 16s 376ms/step - accuracy: 0.5798 - loss: 0.9310
## 23/65 ━━━━━━━━━━━━━━━━━━━━ 15s 379ms/step - accuracy: 0.5814 - loss: 0.9296
## 24/65 ━━━━━━━━━━━━━━━━━━━━ 15s 378ms/step - accuracy: 0.5830 - loss: 0.9281
## 25/65 ━━━━━━━━━━━━━━━━━━━━ 15s 377ms/step - accuracy: 0.5846 - loss: 0.9267
## 26/65 ━━━━━━━━━━━━━━━━━━━━ 14s 377ms/step - accuracy: 0.5861 - loss: 0.9251
## 27/65 ━━━━━━━━━━━━━━━━━━━━ 14s 382ms/step - accuracy: 0.5876 - loss: 0.9236
## 28/65 ━━━━━━━━━━━━━━━━━━━━ 14s 383ms/step - accuracy: 0.5891 - loss: 0.9220
## 29/65 ━━━━━━━━━━━━━━━━━━━━ 13s 384ms/step - accuracy: 0.5904 - loss: 0.9205
## 30/65 ━━━━━━━━━━━━━━━━━━━━ 13s 383ms/step - accuracy: 0.5918 - loss: 0.9190
## 31/65 ━━━━━━━━━━━━━━━━━━━━ 13s 383ms/step - accuracy: 0.5933 - loss: 0.9174
## 32/65 ━━━━━━━━━━━━━━━━━━━━ 12s 377ms/step - accuracy: 0.5946 - loss: 0.9159
## 33/65 ━━━━━━━━━━━━━━━━━━━━ 11s 370ms/step - accuracy: 0.5959 - loss: 0.9143
## 34/65 ━━━━━━━━━━━━━━━━━━━━ 11s 363ms/step - accuracy: 0.5972 - loss: 0.9128
## 35/65 ━━━━━━━━━━━━━━━━━━━━ 10s 356ms/step - accuracy: 0.5983 - loss: 0.9115
## 36/65 ━━━━━━━━━━━━━━━━━━━━ 10s 350ms/step - accuracy: 0.5994 - loss: 0.9101
## 37/65 ━━━━━━━━━━━━━━━━━━━━ 9s 344ms/step - accuracy: 0.6004 - loss: 0.9089 
## 38/65 ━━━━━━━━━━━━━━━━━━━━ 9s 339ms/step - accuracy: 0.6014 - loss: 0.9077
## 39/65 ━━━━━━━━━━━━━━━━━━━━ 8s 334ms/step - accuracy: 0.6025 - loss: 0.9065
## 40/65 ━━━━━━━━━━━━━━━━━━━━ 8s 329ms/step - accuracy: 0.6034 - loss: 0.9054
## 41/65 ━━━━━━━━━━━━━━━━━━━━ 7s 324ms/step - accuracy: 0.6045 - loss: 0.9043
## 42/65 ━━━━━━━━━━━━━━━━━━━━ 7s 320ms/step - accuracy: 0.6055 - loss: 0.9032
## 43/65 ━━━━━━━━━━━━━━━━━━━━ 6s 316ms/step - accuracy: 0.6065 - loss: 0.9021
## 44/65 ━━━━━━━━━━━━━━━━━━━━ 6s 312ms/step - accuracy: 0.6076 - loss: 0.9009
## 45/65 ━━━━━━━━━━━━━━━━━━━━ 6s 308ms/step - accuracy: 0.6087 - loss: 0.8997
## 46/65 ━━━━━━━━━━━━━━━━━━━━ 5s 304ms/step - accuracy: 0.6098 - loss: 0.8984
## 47/65 ━━━━━━━━━━━━━━━━━━━━ 5s 301ms/step - accuracy: 0.6108 - loss: 0.8973
## 48/65 ━━━━━━━━━━━━━━━━━━━━ 5s 297ms/step - accuracy: 0.6118 - loss: 0.8962
## 49/65 ━━━━━━━━━━━━━━━━━━━━ 4s 294ms/step - accuracy: 0.6127 - loss: 0.8952
## 50/65 ━━━━━━━━━━━━━━━━━━━━ 4s 291ms/step - accuracy: 0.6135 - loss: 0.8941
## 51/65 ━━━━━━━━━━━━━━━━━━━━ 4s 288ms/step - accuracy: 0.6143 - loss: 0.8932
## 52/65 ━━━━━━━━━━━━━━━━━━━━ 3s 285ms/step - accuracy: 0.6151 - loss: 0.8923
## 53/65 ━━━━━━━━━━━━━━━━━━━━ 3s 282ms/step - accuracy: 0.6157 - loss: 0.8916
## 54/65 ━━━━━━━━━━━━━━━━━━━━ 3s 279ms/step - accuracy: 0.6164 - loss: 0.8908
## 55/65 ━━━━━━━━━━━━━━━━━━━━ 2s 276ms/step - accuracy: 0.6170 - loss: 0.8900
## 56/65 ━━━━━━━━━━━━━━━━━━━━ 2s 274ms/step - accuracy: 0.6176 - loss: 0.8893
## 57/65 ━━━━━━━━━━━━━━━━━━━━ 2s 272ms/step - accuracy: 0.6182 - loss: 0.8885
## 58/65 ━━━━━━━━━━━━━━━━━━━━ 1s 270ms/step - accuracy: 0.6188 - loss: 0.8878
## 59/65 ━━━━━━━━━━━━━━━━━━━━ 1s 267ms/step - accuracy: 0.6195 - loss: 0.8870
## 60/65 ━━━━━━━━━━━━━━━━━━━━ 1s 265ms/step - accuracy: 0.6201 - loss: 0.8862
## 61/65 ━━━━━━━━━━━━━━━━━━━━ 1s 263ms/step - accuracy: 0.6207 - loss: 0.8854
## 62/65 ━━━━━━━━━━━━━━━━━━━━ 0s 261ms/step - accuracy: 0.6213 - loss: 0.8846
## 63/65 ━━━━━━━━━━━━━━━━━━━━ 0s 259ms/step - accuracy: 0.6218 - loss: 0.8838
## 64/65 ━━━━━━━━━━━━━━━━━━━━ 0s 258ms/step - accuracy: 0.6224 - loss: 0.8830
## 65/65 ━━━━━━━━━━━━━━━━━━━━ 0s 255ms/step - accuracy: 0.6229 - loss: 0.8822
## 65/65 ━━━━━━━━━━━━━━━━━━━━ 25s 279ms/step - accuracy: 0.6569 - loss: 0.8342 - val_accuracy: 0.6979 - val_loss: 0.7725
## Epoch 3/10
## 
##  1/65 ━━━━━━━━━━━━━━━━━━━━ 2:45 3s/step - accuracy: 0.7500 - loss: 0.6462
##  2/65 ━━━━━━━━━━━━━━━━━━━━ 8s 138ms/step - accuracy: 0.7422 - loss: 0.6507
##  3/65 ━━━━━━━━━━━━━━━━━━━━ 8s 137ms/step - accuracy: 0.7378 - loss: 0.6596
##  4/65 ━━━━━━━━━━━━━━━━━━━━ 8s 138ms/step - accuracy: 0.7370 - loss: 0.6673
##  5/65 ━━━━━━━━━━━━━━━━━━━━ 8s 135ms/step - accuracy: 0.7396 - loss: 0.6635
##  6/65 ━━━━━━━━━━━━━━━━━━━━ 7s 135ms/step - accuracy: 0.7396 - loss: 0.6627
##  7/65 ━━━━━━━━━━━━━━━━━━━━ 7s 135ms/step - accuracy: 0.7392 - loss: 0.6622
##  8/65 ━━━━━━━━━━━━━━━━━━━━ 7s 135ms/step - accuracy: 0.7405 - loss: 0.6611
##  9/65 ━━━━━━━━━━━━━━━━━━━━ 7s 134ms/step - accuracy: 0.7423 - loss: 0.6593
## 10/65 ━━━━━━━━━━━━━━━━━━━━ 8s 147ms/step - accuracy: 0.7434 - loss: 0.6581
## 11/65 ━━━━━━━━━━━━━━━━━━━━ 9s 170ms/step - accuracy: 0.7448 - loss: 0.6562
## 12/65 ━━━━━━━━━━━━━━━━━━━━ 8s 168ms/step - accuracy: 0.7459 - loss: 0.6549
## 13/65 ━━━━━━━━━━━━━━━━━━━━ 8s 165ms/step - accuracy: 0.7467 - loss: 0.6535
## 14/65 ━━━━━━━━━━━━━━━━━━━━ 8s 163ms/step - accuracy: 0.7473 - loss: 0.6522
## 15/65 ━━━━━━━━━━━━━━━━━━━━ 8s 161ms/step - accuracy: 0.7478 - loss: 0.6513
## 16/65 ━━━━━━━━━━━━━━━━━━━━ 7s 159ms/step - accuracy: 0.7478 - loss: 0.6509
## 17/65 ━━━━━━━━━━━━━━━━━━━━ 7s 157ms/step - accuracy: 0.7476 - loss: 0.6507
## 18/65 ━━━━━━━━━━━━━━━━━━━━ 7s 156ms/step - accuracy: 0.7472 - loss: 0.6509
## 19/65 ━━━━━━━━━━━━━━━━━━━━ 7s 154ms/step - accuracy: 0.7470 - loss: 0.6509
## 20/65 ━━━━━━━━━━━━━━━━━━━━ 6s 153ms/step - accuracy: 0.7466 - loss: 0.6515
## 21/65 ━━━━━━━━━━━━━━━━━━━━ 6s 152ms/step - accuracy: 0.7462 - loss: 0.6518
## 22/65 ━━━━━━━━━━━━━━━━━━━━ 6s 152ms/step - accuracy: 0.7459 - loss: 0.6519
## 23/65 ━━━━━━━━━━━━━━━━━━━━ 6s 151ms/step - accuracy: 0.7457 - loss: 0.6521
## 24/65 ━━━━━━━━━━━━━━━━━━━━ 6s 151ms/step - accuracy: 0.7456 - loss: 0.6521
## 25/65 ━━━━━━━━━━━━━━━━━━━━ 6s 150ms/step - accuracy: 0.7456 - loss: 0.6518
## 26/65 ━━━━━━━━━━━━━━━━━━━━ 5s 150ms/step - accuracy: 0.7456 - loss: 0.6516
## 27/65 ━━━━━━━━━━━━━━━━━━━━ 5s 149ms/step - accuracy: 0.7456 - loss: 0.6514
## 28/65 ━━━━━━━━━━━━━━━━━━━━ 5s 155ms/step - accuracy: 0.7457 - loss: 0.6511
## 29/65 ━━━━━━━━━━━━━━━━━━━━ 5s 161ms/step - accuracy: 0.7457 - loss: 0.6508
## 30/65 ━━━━━━━━━━━━━━━━━━━━ 5s 160ms/step - accuracy: 0.7458 - loss: 0.6503
## 31/65 ━━━━━━━━━━━━━━━━━━━━ 5s 159ms/step - accuracy: 0.7459 - loss: 0.6499
## 32/65 ━━━━━━━━━━━━━━━━━━━━ 5s 159ms/step - accuracy: 0.7459 - loss: 0.6493
## 33/65 ━━━━━━━━━━━━━━━━━━━━ 5s 158ms/step - accuracy: 0.7459 - loss: 0.6489
## 34/65 ━━━━━━━━━━━━━━━━━━━━ 4s 157ms/step - accuracy: 0.7460 - loss: 0.6484
## 35/65 ━━━━━━━━━━━━━━━━━━━━ 5s 186ms/step - accuracy: 0.7460 - loss: 0.6479
## 36/65 ━━━━━━━━━━━━━━━━━━━━ 5s 184ms/step - accuracy: 0.7461 - loss: 0.6473
## 37/65 ━━━━━━━━━━━━━━━━━━━━ 5s 190ms/step - accuracy: 0.7461 - loss: 0.6467
## 38/65 ━━━━━━━━━━━━━━━━━━━━ 5s 188ms/step - accuracy: 0.7461 - loss: 0.6461
## 39/65 ━━━━━━━━━━━━━━━━━━━━ 4s 187ms/step - accuracy: 0.7460 - loss: 0.6456
## 40/65 ━━━━━━━━━━━━━━━━━━━━ 4s 186ms/step - accuracy: 0.7459 - loss: 0.6452
## 41/65 ━━━━━━━━━━━━━━━━━━━━ 4s 185ms/step - accuracy: 0.7458 - loss: 0.6447
## 42/65 ━━━━━━━━━━━━━━━━━━━━ 4s 184ms/step - accuracy: 0.7458 - loss: 0.6441
## 43/65 ━━━━━━━━━━━━━━━━━━━━ 4s 182ms/step - accuracy: 0.7458 - loss: 0.6435
## 44/65 ━━━━━━━━━━━━━━━━━━━━ 3s 181ms/step - accuracy: 0.7458 - loss: 0.6428
## 45/65 ━━━━━━━━━━━━━━━━━━━━ 3s 180ms/step - accuracy: 0.7458 - loss: 0.6423
## 46/65 ━━━━━━━━━━━━━━━━━━━━ 3s 180ms/step - accuracy: 0.7459 - loss: 0.6417
## 47/65 ━━━━━━━━━━━━━━━━━━━━ 3s 179ms/step - accuracy: 0.7460 - loss: 0.6410
## 48/65 ━━━━━━━━━━━━━━━━━━━━ 3s 178ms/step - accuracy: 0.7462 - loss: 0.6403
## 49/65 ━━━━━━━━━━━━━━━━━━━━ 2s 178ms/step - accuracy: 0.7463 - loss: 0.6397
## 50/65 ━━━━━━━━━━━━━━━━━━━━ 2s 177ms/step - accuracy: 0.7465 - loss: 0.6391
## 51/65 ━━━━━━━━━━━━━━━━━━━━ 2s 176ms/step - accuracy: 0.7466 - loss: 0.6385
## 52/65 ━━━━━━━━━━━━━━━━━━━━ 2s 175ms/step - accuracy: 0.7468 - loss: 0.6379
## 53/65 ━━━━━━━━━━━━━━━━━━━━ 2s 175ms/step - accuracy: 0.7470 - loss: 0.6373
## 54/65 ━━━━━━━━━━━━━━━━━━━━ 1s 179ms/step - accuracy: 0.7472 - loss: 0.6367
## 55/65 ━━━━━━━━━━━━━━━━━━━━ 1s 178ms/step - accuracy: 0.7474 - loss: 0.6361
## 56/65 ━━━━━━━━━━━━━━━━━━━━ 1s 178ms/step - accuracy: 0.7477 - loss: 0.6355
## 57/65 ━━━━━━━━━━━━━━━━━━━━ 1s 177ms/step - accuracy: 0.7479 - loss: 0.6349
## 58/65 ━━━━━━━━━━━━━━━━━━━━ 1s 176ms/step - accuracy: 0.7481 - loss: 0.6343
## 59/65 ━━━━━━━━━━━━━━━━━━━━ 1s 175ms/step - accuracy: 0.7484 - loss: 0.6337
## 60/65 ━━━━━━━━━━━━━━━━━━━━ 0s 175ms/step - accuracy: 0.7486 - loss: 0.6331
## 61/65 ━━━━━━━━━━━━━━━━━━━━ 0s 174ms/step - accuracy: 0.7489 - loss: 0.6325
## 62/65 ━━━━━━━━━━━━━━━━━━━━ 0s 173ms/step - accuracy: 0.7491 - loss: 0.6318
## 63/65 ━━━━━━━━━━━━━━━━━━━━ 0s 173ms/step - accuracy: 0.7494 - loss: 0.6312
## 64/65 ━━━━━━━━━━━━━━━━━━━━ 0s 172ms/step - accuracy: 0.7496 - loss: 0.6305
## 65/65 ━━━━━━━━━━━━━━━━━━━━ 0s 170ms/step - accuracy: 0.7499 - loss: 0.6298
## 65/65 ━━━━━━━━━━━━━━━━━━━━ 15s 192ms/step - accuracy: 0.7662 - loss: 0.5878 - val_accuracy: 0.7193 - val_loss: 0.7048
## Epoch 4/10
## 
##  1/65 ━━━━━━━━━━━━━━━━━━━━ 19s 297ms/step - accuracy: 0.8750 - loss: 0.4094
##  2/65 ━━━━━━━━━━━━━━━━━━━━ 8s 133ms/step - accuracy: 0.8672 - loss: 0.4240 
##  3/65 ━━━━━━━━━━━━━━━━━━━━ 8s 130ms/step - accuracy: 0.8698 - loss: 0.4122
##  4/65 ━━━━━━━━━━━━━━━━━━━━ 8s 134ms/step - accuracy: 0.8691 - loss: 0.4173
##  5/65 ━━━━━━━━━━━━━━━━━━━━ 7s 133ms/step - accuracy: 0.8603 - loss: 0.4282
##  6/65 ━━━━━━━━━━━━━━━━━━━━ 8s 140ms/step - accuracy: 0.8515 - loss: 0.4396
##  7/65 ━━━━━━━━━━━━━━━━━━━━ 9s 160ms/step - accuracy: 0.8427 - loss: 0.4499
##  8/65 ━━━━━━━━━━━━━━━━━━━━ 9s 170ms/step - accuracy: 0.8375 - loss: 0.4537
##  9/65 ━━━━━━━━━━━━━━━━━━━━ 9s 174ms/step - accuracy: 0.8343 - loss: 0.4554
## 10/65 ━━━━━━━━━━━━━━━━━━━━ 9s 172ms/step - accuracy: 0.8318 - loss: 0.4571
## 11/65 ━━━━━━━━━━━━━━━━━━━━ 9s 170ms/step - accuracy: 0.8290 - loss: 0.4586
## 12/65 ━━━━━━━━━━━━━━━━━━━━ 9s 179ms/step - accuracy: 0.8266 - loss: 0.4600
## 13/65 ━━━━━━━━━━━━━━━━━━━━ 10s 199ms/step - accuracy: 0.8244 - loss: 0.4617
## 14/65 ━━━━━━━━━━━━━━━━━━━━ 10s 213ms/step - accuracy: 0.8229 - loss: 0.4633
## 15/65 ━━━━━━━━━━━━━━━━━━━━ 11s 224ms/step - accuracy: 0.8221 - loss: 0.4640
## 16/65 ━━━━━━━━━━━━━━━━━━━━ 11s 234ms/step - accuracy: 0.8216 - loss: 0.4639
## 17/65 ━━━━━━━━━━━━━━━━━━━━ 11s 243ms/step - accuracy: 0.8213 - loss: 0.4646
## 18/65 ━━━━━━━━━━━━━━━━━━━━ 11s 239ms/step - accuracy: 0.8213 - loss: 0.4649
## 19/65 ━━━━━━━━━━━━━━━━━━━━ 11s 242ms/step - accuracy: 0.8213 - loss: 0.4651
## 20/65 ━━━━━━━━━━━━━━━━━━━━ 11s 251ms/step - accuracy: 0.8212 - loss: 0.4655
## 21/65 ━━━━━━━━━━━━━━━━━━━━ 11s 258ms/step - accuracy: 0.8211 - loss: 0.4658
## 22/65 ━━━━━━━━━━━━━━━━━━━━ 11s 262ms/step - accuracy: 0.8212 - loss: 0.4659
## 23/65 ━━━━━━━━━━━━━━━━━━━━ 12s 303ms/step - accuracy: 0.8213 - loss: 0.4659
## 24/65 ━━━━━━━━━━━━━━━━━━━━ 12s 296ms/step - accuracy: 0.8214 - loss: 0.4658
## 25/65 ━━━━━━━━━━━━━━━━━━━━ 11s 289ms/step - accuracy: 0.8218 - loss: 0.4655
## 26/65 ━━━━━━━━━━━━━━━━━━━━ 11s 283ms/step - accuracy: 0.8222 - loss: 0.4649
## 27/65 ━━━━━━━━━━━━━━━━━━━━ 10s 277ms/step - accuracy: 0.8228 - loss: 0.4641
## 28/65 ━━━━━━━━━━━━━━━━━━━━ 10s 272ms/step - accuracy: 0.8234 - loss: 0.4632
## 29/65 ━━━━━━━━━━━━━━━━━━━━ 9s 267ms/step - accuracy: 0.8241 - loss: 0.4623 
## 30/65 ━━━━━━━━━━━━━━━━━━━━ 9s 263ms/step - accuracy: 0.8246 - loss: 0.4615
## 31/65 ━━━━━━━━━━━━━━━━━━━━ 8s 258ms/step - accuracy: 0.8253 - loss: 0.4604
## 32/65 ━━━━━━━━━━━━━━━━━━━━ 8s 255ms/step - accuracy: 0.8260 - loss: 0.4593
## 33/65 ━━━━━━━━━━━━━━━━━━━━ 8s 251ms/step - accuracy: 0.8267 - loss: 0.4582
## 34/65 ━━━━━━━━━━━━━━━━━━━━ 7s 247ms/step - accuracy: 0.8274 - loss: 0.4573
## 35/65 ━━━━━━━━━━━━━━━━━━━━ 7s 244ms/step - accuracy: 0.8280 - loss: 0.4563
## 36/65 ━━━━━━━━━━━━━━━━━━━━ 6s 241ms/step - accuracy: 0.8287 - loss: 0.4553
## 37/65 ━━━━━━━━━━━━━━━━━━━━ 6s 238ms/step - accuracy: 0.8294 - loss: 0.4542
## 38/65 ━━━━━━━━━━━━━━━━━━━━ 6s 235ms/step - accuracy: 0.8300 - loss: 0.4532
## 39/65 ━━━━━━━━━━━━━━━━━━━━ 6s 235ms/step - accuracy: 0.8306 - loss: 0.4522
## 40/65 ━━━━━━━━━━━━━━━━━━━━ 5s 233ms/step - accuracy: 0.8312 - loss: 0.4513
## 41/65 ━━━━━━━━━━━━━━━━━━━━ 5s 230ms/step - accuracy: 0.8318 - loss: 0.4503
## 42/65 ━━━━━━━━━━━━━━━━━━━━ 5s 228ms/step - accuracy: 0.8323 - loss: 0.4494
## 43/65 ━━━━━━━━━━━━━━━━━━━━ 4s 226ms/step - accuracy: 0.8329 - loss: 0.4484
## 44/65 ━━━━━━━━━━━━━━━━━━━━ 4s 224ms/step - accuracy: 0.8334 - loss: 0.4475
## 45/65 ━━━━━━━━━━━━━━━━━━━━ 4s 222ms/step - accuracy: 0.8339 - loss: 0.4466
## 46/65 ━━━━━━━━━━━━━━━━━━━━ 4s 220ms/step - accuracy: 0.8344 - loss: 0.4457
## 47/65 ━━━━━━━━━━━━━━━━━━━━ 3s 220ms/step - accuracy: 0.8349 - loss: 0.4448
## 48/65 ━━━━━━━━━━━━━━━━━━━━ 3s 218ms/step - accuracy: 0.8354 - loss: 0.4440
## 49/65 ━━━━━━━━━━━━━━━━━━━━ 3s 216ms/step - accuracy: 0.8357 - loss: 0.4433
## 50/65 ━━━━━━━━━━━━━━━━━━━━ 3s 222ms/step - accuracy: 0.8361 - loss: 0.4426
## 51/65 ━━━━━━━━━━━━━━━━━━━━ 3s 232ms/step - accuracy: 0.8364 - loss: 0.4420
## 52/65 ━━━━━━━━━━━━━━━━━━━━ 3s 301ms/step - accuracy: 0.8368 - loss: 0.4413
## 53/65 ━━━━━━━━━━━━━━━━━━━━ 3s 309ms/step - accuracy: 0.8371 - loss: 0.4406
## 54/65 ━━━━━━━━━━━━━━━━━━━━ 3s 326ms/step - accuracy: 0.8374 - loss: 0.4401
## 55/65 ━━━━━━━━━━━━━━━━━━━━ 3s 326ms/step - accuracy: 0.8377 - loss: 0.4396
## 56/65 ━━━━━━━━━━━━━━━━━━━━ 2s 326ms/step - accuracy: 0.8379 - loss: 0.4392
## 57/65 ━━━━━━━━━━━━━━━━━━━━ 2s 329ms/step - accuracy: 0.8382 - loss: 0.4387
## 58/65 ━━━━━━━━━━━━━━━━━━━━ 2s 328ms/step - accuracy: 0.8385 - loss: 0.4382
## 59/65 ━━━━━━━━━━━━━━━━━━━━ 1s 326ms/step - accuracy: 0.8388 - loss: 0.4378
## 60/65 ━━━━━━━━━━━━━━━━━━━━ 1s 324ms/step - accuracy: 0.8391 - loss: 0.4373
## 61/65 ━━━━━━━━━━━━━━━━━━━━ 1s 321ms/step - accuracy: 0.8393 - loss: 0.4369
## 62/65 ━━━━━━━━━━━━━━━━━━━━ 0s 321ms/step - accuracy: 0.8396 - loss: 0.4365
## 63/65 ━━━━━━━━━━━━━━━━━━━━ 0s 320ms/step - accuracy: 0.8398 - loss: 0.4361
## 64/65 ━━━━━━━━━━━━━━━━━━━━ 0s 317ms/step - accuracy: 0.8401 - loss: 0.4356
## 65/65 ━━━━━━━━━━━━━━━━━━━━ 0s 313ms/step - accuracy: 0.8404 - loss: 0.4351
## 65/65 ━━━━━━━━━━━━━━━━━━━━ 22s 335ms/step - accuracy: 0.8565 - loss: 0.4059 - val_accuracy: 0.7115 - val_loss: 0.8345
## Epoch 5/10
## 
##  1/65 ━━━━━━━━━━━━━━━━━━━━ 22:03 21s/step - accuracy: 0.9062 - loss: 0.2126
##  2/65 ━━━━━━━━━━━━━━━━━━━━ 15s 247ms/step - accuracy: 0.9062 - loss: 0.2151
##  3/65 ━━━━━━━━━━━━━━━━━━━━ 14s 230ms/step - accuracy: 0.9132 - loss: 0.2132
##  4/65 ━━━━━━━━━━━━━━━━━━━━ 12s 207ms/step - accuracy: 0.9193 - loss: 0.2124
##  5/65 ━━━━━━━━━━━━━━━━━━━━ 11s 197ms/step - accuracy: 0.9204 - loss: 0.2171
##  6/65 ━━━━━━━━━━━━━━━━━━━━ 11s 190ms/step - accuracy: 0.9198 - loss: 0.2253
##  7/65 ━━━━━━━━━━━━━━━━━━━━ 10s 187ms/step - accuracy: 0.9191 - loss: 0.2351
##  8/65 ━━━━━━━━━━━━━━━━━━━━ 11s 195ms/step - accuracy: 0.9190 - loss: 0.2413
##  9/65 ━━━━━━━━━━━━━━━━━━━━ 10s 193ms/step - accuracy: 0.9191 - loss: 0.2442
## 10/65 ━━━━━━━━━━━━━━━━━━━━ 10s 189ms/step - accuracy: 0.9194 - loss: 0.2461
## 11/65 ━━━━━━━━━━━━━━━━━━━━ 10s 186ms/step - accuracy: 0.9200 - loss: 0.2466
## 12/65 ━━━━━━━━━━━━━━━━━━━━ 14s 266ms/step - accuracy: 0.9210 - loss: 0.2465
## 13/65 ━━━━━━━━━━━━━━━━━━━━ 15s 289ms/step - accuracy: 0.9221 - loss: 0.2463
## 14/65 ━━━━━━━━━━━━━━━━━━━━ 16s 327ms/step - accuracy: 0.9231 - loss: 0.2461
## 15/65 ━━━━━━━━━━━━━━━━━━━━ 18s 363ms/step - accuracy: 0.9242 - loss: 0.2455
## 16/65 ━━━━━━━━━━━━━━━━━━━━ 18s 380ms/step - accuracy: 0.9252 - loss: 0.2448
## 17/65 ━━━━━━━━━━━━━━━━━━━━ 19s 413ms/step - accuracy: 0.9262 - loss: 0.2442
## 18/65 ━━━━━━━━━━━━━━━━━━━━ 19s 419ms/step - accuracy: 0.9271 - loss: 0.2437
## 19/65 ━━━━━━━━━━━━━━━━━━━━ 20s 440ms/step - accuracy: 0.9280 - loss: 0.2429
## 20/65 ━━━━━━━━━━━━━━━━━━━━ 20s 445ms/step - accuracy: 0.9287 - loss: 0.2426
## 21/65 ━━━━━━━━━━━━━━━━━━━━ 19s 442ms/step - accuracy: 0.9291 - loss: 0.2425
## 22/65 ━━━━━━━━━━━━━━━━━━━━ 18s 430ms/step - accuracy: 0.9293 - loss: 0.2429
## 23/65 ━━━━━━━━━━━━━━━━━━━━ 17s 420ms/step - accuracy: 0.9294 - loss: 0.2434
## 24/65 ━━━━━━━━━━━━━━━━━━━━ 16s 410ms/step - accuracy: 0.9294 - loss: 0.2441
## 25/65 ━━━━━━━━━━━━━━━━━━━━ 16s 401ms/step - accuracy: 0.9293 - loss: 0.2449
## 26/65 ━━━━━━━━━━━━━━━━━━━━ 15s 391ms/step - accuracy: 0.9293 - loss: 0.2456
## 27/65 ━━━━━━━━━━━━━━━━━━━━ 14s 382ms/step - accuracy: 0.9292 - loss: 0.2464
## 28/65 ━━━━━━━━━━━━━━━━━━━━ 13s 374ms/step - accuracy: 0.9291 - loss: 0.2474
## 29/65 ━━━━━━━━━━━━━━━━━━━━ 13s 368ms/step - accuracy: 0.9291 - loss: 0.2482
## 30/65 ━━━━━━━━━━━━━━━━━━━━ 12s 364ms/step - accuracy: 0.9291 - loss: 0.2490
## 31/65 ━━━━━━━━━━━━━━━━━━━━ 12s 358ms/step - accuracy: 0.9290 - loss: 0.2498
## 32/65 ━━━━━━━━━━━━━━━━━━━━ 11s 353ms/step - accuracy: 0.9289 - loss: 0.2506
## 33/65 ━━━━━━━━━━━━━━━━━━━━ 11s 347ms/step - accuracy: 0.9288 - loss: 0.2513
## 34/65 ━━━━━━━━━━━━━━━━━━━━ 10s 341ms/step - accuracy: 0.9287 - loss: 0.2519
## 35/65 ━━━━━━━━━━━━━━━━━━━━ 10s 337ms/step - accuracy: 0.9286 - loss: 0.2526
## 36/65 ━━━━━━━━━━━━━━━━━━━━ 9s 332ms/step - accuracy: 0.9285 - loss: 0.2532 
## 37/65 ━━━━━━━━━━━━━━━━━━━━ 9s 326ms/step - accuracy: 0.9285 - loss: 0.2536
## 38/65 ━━━━━━━━━━━━━━━━━━━━ 8s 322ms/step - accuracy: 0.9284 - loss: 0.2540
## 39/65 ━━━━━━━━━━━━━━━━━━━━ 8s 317ms/step - accuracy: 0.9283 - loss: 0.2543
## 40/65 ━━━━━━━━━━━━━━━━━━━━ 7s 313ms/step - accuracy: 0.9282 - loss: 0.2545
## 41/65 ━━━━━━━━━━━━━━━━━━━━ 7s 310ms/step - accuracy: 0.9282 - loss: 0.2546
## 42/65 ━━━━━━━━━━━━━━━━━━━━ 7s 306ms/step - accuracy: 0.9282 - loss: 0.2547
## 43/65 ━━━━━━━━━━━━━━━━━━━━ 6s 302ms/step - accuracy: 0.9282 - loss: 0.2547
## 44/65 ━━━━━━━━━━━━━━━━━━━━ 6s 299ms/step - accuracy: 0.9283 - loss: 0.2547
## 45/65 ━━━━━━━━━━━━━━━━━━━━ 5s 296ms/step - accuracy: 0.9283 - loss: 0.2547
## 46/65 ━━━━━━━━━━━━━━━━━━━━ 5s 293ms/step - accuracy: 0.9283 - loss: 0.2547
## 47/65 ━━━━━━━━━━━━━━━━━━━━ 5s 290ms/step - accuracy: 0.9283 - loss: 0.2546
## 48/65 ━━━━━━━━━━━━━━━━━━━━ 4s 288ms/step - accuracy: 0.9284 - loss: 0.2545
## 49/65 ━━━━━━━━━━━━━━━━━━━━ 4s 285ms/step - accuracy: 0.9284 - loss: 0.2543
## 50/65 ━━━━━━━━━━━━━━━━━━━━ 4s 282ms/step - accuracy: 0.9285 - loss: 0.2541
## 51/65 ━━━━━━━━━━━━━━━━━━━━ 3s 280ms/step - accuracy: 0.9286 - loss: 0.2538
## 52/65 ━━━━━━━━━━━━━━━━━━━━ 3s 277ms/step - accuracy: 0.9287 - loss: 0.2535
## 53/65 ━━━━━━━━━━━━━━━━━━━━ 3s 274ms/step - accuracy: 0.9288 - loss: 0.2533
## 54/65 ━━━━━━━━━━━━━━━━━━━━ 2s 272ms/step - accuracy: 0.9289 - loss: 0.2530
## 55/65 ━━━━━━━━━━━━━━━━━━━━ 2s 270ms/step - accuracy: 0.9289 - loss: 0.2527
## 56/65 ━━━━━━━━━━━━━━━━━━━━ 2s 267ms/step - accuracy: 0.9290 - loss: 0.2524
## 57/65 ━━━━━━━━━━━━━━━━━━━━ 2s 265ms/step - accuracy: 0.9290 - loss: 0.2521
## 58/65 ━━━━━━━━━━━━━━━━━━━━ 1s 264ms/step - accuracy: 0.9291 - loss: 0.2519
## 59/65 ━━━━━━━━━━━━━━━━━━━━ 1s 262ms/step - accuracy: 0.9291 - loss: 0.2517
## 60/65 ━━━━━━━━━━━━━━━━━━━━ 1s 260ms/step - accuracy: 0.9291 - loss: 0.2515
## 61/65 ━━━━━━━━━━━━━━━━━━━━ 1s 258ms/step - accuracy: 0.9292 - loss: 0.2513
## 62/65 ━━━━━━━━━━━━━━━━━━━━ 0s 257ms/step - accuracy: 0.9292 - loss: 0.2511
## 63/65 ━━━━━━━━━━━━━━━━━━━━ 0s 256ms/step - accuracy: 0.9292 - loss: 0.2508
## 64/65 ━━━━━━━━━━━━━━━━━━━━ 0s 255ms/step - accuracy: 0.9293 - loss: 0.2506
## 65/65 ━━━━━━━━━━━━━━━━━━━━ 0s 252ms/step - accuracy: 0.9293 - loss: 0.2504
## 65/65 ━━━━━━━━━━━━━━━━━━━━ 38s 274ms/step - accuracy: 0.9317 - loss: 0.2360 - val_accuracy: 0.7076 - val_loss: 0.9437
## Epoch 6/10
## 
##  1/65 ━━━━━━━━━━━━━━━━━━━━ 3:06 3s/step - accuracy: 0.9375 - loss: 0.1527
##  2/65 ━━━━━━━━━━━━━━━━━━━━ 16s 263ms/step - accuracy: 0.9375 - loss: 0.1646
##  3/65 ━━━━━━━━━━━━━━━━━━━━ 14s 230ms/step - accuracy: 0.9375 - loss: 0.1636
##  4/65 ━━━━━━━━━━━━━━━━━━━━ 14s 242ms/step - accuracy: 0.9414 - loss: 0.1608
##  5/65 ━━━━━━━━━━━━━━━━━━━━ 15s 250ms/step - accuracy: 0.9456 - loss: 0.1545
##  6/65 ━━━━━━━━━━━━━━━━━━━━ 13s 237ms/step - accuracy: 0.9486 - loss: 0.1488
##  7/65 ━━━━━━━━━━━━━━━━━━━━ 13s 233ms/step - accuracy: 0.9515 - loss: 0.1439
##  8/65 ━━━━━━━━━━━━━━━━━━━━ 12s 224ms/step - accuracy: 0.9536 - loss: 0.1401
##  9/65 ━━━━━━━━━━━━━━━━━━━━ 12s 232ms/step - accuracy: 0.9553 - loss: 0.1367
## 10/65 ━━━━━━━━━━━━━━━━━━━━ 12s 231ms/step - accuracy: 0.9567 - loss: 0.1337
## 11/65 ━━━━━━━━━━━━━━━━━━━━ 12s 227ms/step - accuracy: 0.9580 - loss: 0.1307
## 12/65 ━━━━━━━━━━━━━━━━━━━━ 11s 226ms/step - accuracy: 0.9591 - loss: 0.1291
## 13/65 ━━━━━━━━━━━━━━━━━━━━ 11s 221ms/step - accuracy: 0.9599 - loss: 0.1279
## 14/65 ━━━━━━━━━━━━━━━━━━━━ 11s 216ms/step - accuracy: 0.9605 - loss: 0.1272
## 15/65 ━━━━━━━━━━━━━━━━━━━━ 10s 214ms/step - accuracy: 0.9609 - loss: 0.1271
## 16/65 ━━━━━━━━━━━━━━━━━━━━ 10s 216ms/step - accuracy: 0.9613 - loss: 0.1268
## 17/65 ━━━━━━━━━━━━━━━━━━━━ 10s 213ms/step - accuracy: 0.9616 - loss: 0.1266
## 18/65 ━━━━━━━━━━━━━━━━━━━━ 9s 212ms/step - accuracy: 0.9616 - loss: 0.1270 
## 19/65 ━━━━━━━━━━━━━━━━━━━━ 9s 210ms/step - accuracy: 0.9617 - loss: 0.1273
## 20/65 ━━━━━━━━━━━━━━━━━━━━ 9s 210ms/step - accuracy: 0.9617 - loss: 0.1281
## 21/65 ━━━━━━━━━━━━━━━━━━━━ 9s 208ms/step - accuracy: 0.9618 - loss: 0.1285
## 22/65 ━━━━━━━━━━━━━━━━━━━━ 8s 209ms/step - accuracy: 0.9617 - loss: 0.1292
## 23/65 ━━━━━━━━━━━━━━━━━━━━ 8s 207ms/step - accuracy: 0.9617 - loss: 0.1303
## 24/65 ━━━━━━━━━━━━━━━━━━━━ 8s 204ms/step - accuracy: 0.9617 - loss: 0.1311
## 25/65 ━━━━━━━━━━━━━━━━━━━━ 8s 202ms/step - accuracy: 0.9617 - loss: 0.1319
## 26/65 ━━━━━━━━━━━━━━━━━━━━ 7s 205ms/step - accuracy: 0.9617 - loss: 0.1325
## 27/65 ━━━━━━━━━━━━━━━━━━━━ 7s 206ms/step - accuracy: 0.9616 - loss: 0.1332
## 28/65 ━━━━━━━━━━━━━━━━━━━━ 7s 207ms/step - accuracy: 0.9616 - loss: 0.1337
## 29/65 ━━━━━━━━━━━━━━━━━━━━ 7s 208ms/step - accuracy: 0.9616 - loss: 0.1341
## 30/65 ━━━━━━━━━━━━━━━━━━━━ 7s 207ms/step - accuracy: 0.9616 - loss: 0.1344
## 31/65 ━━━━━━━━━━━━━━━━━━━━ 7s 208ms/step - accuracy: 0.9616 - loss: 0.1347
## 32/65 ━━━━━━━━━━━━━━━━━━━━ 6s 211ms/step - accuracy: 0.9616 - loss: 0.1349
## 33/65 ━━━━━━━━━━━━━━━━━━━━ 6s 211ms/step - accuracy: 0.9617 - loss: 0.1350
## 34/65 ━━━━━━━━━━━━━━━━━━━━ 6s 211ms/step - accuracy: 0.9617 - loss: 0.1352
## 35/65 ━━━━━━━━━━━━━━━━━━━━ 6s 215ms/step - accuracy: 0.9617 - loss: 0.1353
## 36/65 ━━━━━━━━━━━━━━━━━━━━ 6s 215ms/step - accuracy: 0.9618 - loss: 0.1354
## 37/65 ━━━━━━━━━━━━━━━━━━━━ 6s 215ms/step - accuracy: 0.9618 - loss: 0.1355
## 38/65 ━━━━━━━━━━━━━━━━━━━━ 5s 214ms/step - accuracy: 0.9618 - loss: 0.1356
## 39/65 ━━━━━━━━━━━━━━━━━━━━ 5s 213ms/step - accuracy: 0.9619 - loss: 0.1357
## 40/65 ━━━━━━━━━━━━━━━━━━━━ 5s 212ms/step - accuracy: 0.9619 - loss: 0.1357
## 41/65 ━━━━━━━━━━━━━━━━━━━━ 5s 210ms/step - accuracy: 0.9619 - loss: 0.1358
## 42/65 ━━━━━━━━━━━━━━━━━━━━ 4s 216ms/step - accuracy: 0.9620 - loss: 0.1358
## 43/65 ━━━━━━━━━━━━━━━━━━━━ 5s 229ms/step - accuracy: 0.9620 - loss: 0.1358
## 44/65 ━━━━━━━━━━━━━━━━━━━━ 5s 246ms/step - accuracy: 0.9620 - loss: 0.1358
## 45/65 ━━━━━━━━━━━━━━━━━━━━ 5s 252ms/step - accuracy: 0.9621 - loss: 0.1359
## 46/65 ━━━━━━━━━━━━━━━━━━━━ 4s 250ms/step - accuracy: 0.9621 - loss: 0.1360
## 47/65 ━━━━━━━━━━━━━━━━━━━━ 4s 250ms/step - accuracy: 0.9621 - loss: 0.1360
## 48/65 ━━━━━━━━━━━━━━━━━━━━ 4s 249ms/step - accuracy: 0.9621 - loss: 0.1359
## 49/65 ━━━━━━━━━━━━━━━━━━━━ 4s 252ms/step - accuracy: 0.9621 - loss: 0.1360
## 50/65 ━━━━━━━━━━━━━━━━━━━━ 3s 252ms/step - accuracy: 0.9621 - loss: 0.1361
## 51/65 ━━━━━━━━━━━━━━━━━━━━ 3s 251ms/step - accuracy: 0.9621 - loss: 0.1362
## 52/65 ━━━━━━━━━━━━━━━━━━━━ 3s 249ms/step - accuracy: 0.9621 - loss: 0.1364
## 53/65 ━━━━━━━━━━━━━━━━━━━━ 2s 247ms/step - accuracy: 0.9621 - loss: 0.1364
## 54/65 ━━━━━━━━━━━━━━━━━━━━ 2s 246ms/step - accuracy: 0.9621 - loss: 0.1365
## 55/65 ━━━━━━━━━━━━━━━━━━━━ 2s 244ms/step - accuracy: 0.9622 - loss: 0.1365
## 56/65 ━━━━━━━━━━━━━━━━━━━━ 2s 243ms/step - accuracy: 0.9622 - loss: 0.1366
## 57/65 ━━━━━━━━━━━━━━━━━━━━ 1s 242ms/step - accuracy: 0.9622 - loss: 0.1367
## 58/65 ━━━━━━━━━━━━━━━━━━━━ 1s 241ms/step - accuracy: 0.9622 - loss: 0.1367
## 59/65 ━━━━━━━━━━━━━━━━━━━━ 1s 239ms/step - accuracy: 0.9622 - loss: 0.1368
## 60/65 ━━━━━━━━━━━━━━━━━━━━ 1s 238ms/step - accuracy: 0.9622 - loss: 0.1369
## 61/65 ━━━━━━━━━━━━━━━━━━━━ 0s 237ms/step - accuracy: 0.9622 - loss: 0.1369
## 62/65 ━━━━━━━━━━━━━━━━━━━━ 0s 236ms/step - accuracy: 0.9622 - loss: 0.1370
## 63/65 ━━━━━━━━━━━━━━━━━━━━ 0s 235ms/step - accuracy: 0.9622 - loss: 0.1370
## 64/65 ━━━━━━━━━━━━━━━━━━━━ 0s 234ms/step - accuracy: 0.9622 - loss: 0.1371
## 65/65 ━━━━━━━━━━━━━━━━━━━━ 0s 231ms/step - accuracy: 0.9622 - loss: 0.1371
## 65/65 ━━━━━━━━━━━━━━━━━━━━ 19s 253ms/step - accuracy: 0.9614 - loss: 0.1410 - val_accuracy: 0.7583 - val_loss: 0.9659

# =========================
# HISTORY
# =========================
hist <- history$history

df_hist <- data.frame(
  epoch = 1:length(hist$loss),
  loss = hist$loss,
  val_loss = hist$val_loss,
  accuracy = hist$accuracy,
  val_accuracy = hist$val_accuracy
)

# =========================
# PLOT
# =========================
ggplot(df_hist, aes(x = epoch)) +
  geom_line(aes(y = loss, color = "Train"), size = 1.2) +
  geom_line(aes(y = val_loss, color = "Val"), size = 1.2) +
  labs(title = "Loss Model") +
  theme_minimal()

## Warning: Using `size` aesthetic for lines was deprecated in ggplot2 3.4.0.
## ℹ Please use `linewidth` instead.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.

ggplot(df_hist, aes(x = epoch)) +
  geom_line(aes(y = accuracy, color = "Train"), size = 1.2) +
  geom_line(aes(y = val_accuracy, color = "Val"), size = 1.2) +
  labs(title = "Accuracy Model") +
  theme_minimal()

# =========================
# EVALUASI
# =========================
model$evaluate(x_test, y_test)

## 
##  1/21 ━━━━━━━━━━━━━━━━━━━━ 1s 94ms/step - accuracy: 0.8125 - loss: 0.6393
##  3/21 ━━━━━━━━━━━━━━━━━━━━ 0s 41ms/step - accuracy: 0.7778 - loss: 0.6869
##  5/21 ━━━━━━━━━━━━━━━━━━━━ 0s 44ms/step - accuracy: 0.7598 - loss: 0.7114
##  6/21 ━━━━━━━━━━━━━━━━━━━━ 0s 45ms/step - accuracy: 0.7564 - loss: 0.7139
##  7/21 ━━━━━━━━━━━━━━━━━━━━ 0s 48ms/step - accuracy: 0.7568 - loss: 0.7081
##  8/21 ━━━━━━━━━━━━━━━━━━━━ 0s 49ms/step - accuracy: 0.7550 - loss: 0.7037
## 10/21 ━━━━━━━━━━━━━━━━━━━━ 0s 49ms/step - accuracy: 0.7510 - loss: 0.6966
## 11/21 ━━━━━━━━━━━━━━━━━━━━ 0s 54ms/step - accuracy: 0.7504 - loss: 0.6920
## 12/21 ━━━━━━━━━━━━━━━━━━━━ 0s 55ms/step - accuracy: 0.7495 - loss: 0.6892
## 13/21 ━━━━━━━━━━━━━━━━━━━━ 0s 56ms/step - accuracy: 0.7485 - loss: 0.6870
## 14/21 ━━━━━━━━━━━━━━━━━━━━ 0s 56ms/step - accuracy: 0.7475 - loss: 0.6851
## 15/21 ━━━━━━━━━━━━━━━━━━━━ 0s 57ms/step - accuracy: 0.7467 - loss: 0.6829
## 17/21 ━━━━━━━━━━━━━━━━━━━━ 0s 56ms/step - accuracy: 0.7449 - loss: 0.6816
## 19/21 ━━━━━━━━━━━━━━━━━━━━ 0s 55ms/step - accuracy: 0.7439 - loss: 0.6801
## 20/21 ━━━━━━━━━━━━━━━━━━━━ 0s 55ms/step - accuracy: 0.7435 - loss: 0.6797
## 21/21 ━━━━━━━━━━━━━━━━━━━━ 1s 55ms/step - accuracy: 0.7332 - loss: 0.6741

## [1] 0.6740768 0.7332293

pred <- model$predict(x_test)

## 
##  1/21 ━━━━━━━━━━━━━━━━━━━━ 49s 2s/step
##  2/21 ━━━━━━━━━━━━━━━━━━━━ 1s 54ms/step
##  3/21 ━━━━━━━━━━━━━━━━━━━━ 1s 56ms/step
##  4/21 ━━━━━━━━━━━━━━━━━━━━ 1s 63ms/step
##  5/21 ━━━━━━━━━━━━━━━━━━━━ 1s 64ms/step
##  6/21 ━━━━━━━━━━━━━━━━━━━━ 0s 63ms/step
##  8/21 ━━━━━━━━━━━━━━━━━━━━ 0s 59ms/step
##  9/21 ━━━━━━━━━━━━━━━━━━━━ 0s 60ms/step
## 10/21 ━━━━━━━━━━━━━━━━━━━━ 0s 77ms/step
## 11/21 ━━━━━━━━━━━━━━━━━━━━ 1s 117ms/step
## 12/21 ━━━━━━━━━━━━━━━━━━━━ 1s 119ms/step
## 13/21 ━━━━━━━━━━━━━━━━━━━━ 0s 117ms/step
## 14/21 ━━━━━━━━━━━━━━━━━━━━ 0s 117ms/step
## 15/21 ━━━━━━━━━━━━━━━━━━━━ 0s 115ms/step
## 16/21 ━━━━━━━━━━━━━━━━━━━━ 0s 113ms/step
## 17/21 ━━━━━━━━━━━━━━━━━━━━ 0s 110ms/step
## 18/21 ━━━━━━━━━━━━━━━━━━━━ 0s 108ms/step
## 19/21 ━━━━━━━━━━━━━━━━━━━━ 0s 105ms/step
## 20/21 ━━━━━━━━━━━━━━━━━━━━ 0s 103ms/step
## 21/21 ━━━━━━━━━━━━━━━━━━━━ 0s 173ms/step
## 21/21 ━━━━━━━━━━━━━━━━━━━━ 6s 175ms/step

pred

##              [,1]        [,2]       [,3]
##   [1,] 0.85905600 0.036107987 0.10483602
##   [2,] 0.98501855 0.002803175 0.01217829
##   [3,] 0.12452923 0.607412100 0.26805869
##   [4,] 0.89642566 0.027822861 0.07575145
##   [5,] 0.89335531 0.028840104 0.07780452
##   [6,] 0.13117367 0.598959208 0.26986712
##   [7,] 0.38314340 0.258399278 0.35845739
##   [8,] 0.88367236 0.032214802 0.08411285
##   [9,] 0.14910637 0.564672291 0.28622130
##  [10,] 0.91170639 0.023066796 0.06522671
##  [11,] 0.95693487 0.009000611 0.03406459
##  [12,] 0.93499076 0.015774952 0.04923428
##  [13,] 0.98501855 0.002803175 0.01217829
##  [14,] 0.65281987 0.101589784 0.24559033
##  [15,] 0.03420401 0.858148217 0.10764785
##  [16,] 0.09813240 0.672058463 0.22980911
##  [17,] 0.78957254 0.060207590 0.15021986
##  [18,] 0.17100485 0.500312686 0.32868245
##  [19,] 0.95990282 0.008601435 0.03149575
##  [20,] 0.90838957 0.021781638 0.06982871
##  [21,] 0.88198602 0.030600397 0.08741350
##  [22,] 0.04426560 0.825733304 0.13000107
##  [23,] 0.95151991 0.010485201 0.03799487
##  [24,] 0.28768110 0.343789190 0.36852974
##  [25,] 0.98501855 0.002803175 0.01217829
##  [26,] 0.04426560 0.825733304 0.13000107
##  [27,] 0.94708496 0.011781353 0.04113368
##  [28,] 0.12049062 0.632861435 0.24664798
##  [29,] 0.05548335 0.791443050 0.15307355
##  [30,] 0.88753283 0.030970579 0.08149650
##  [31,] 0.05846886 0.783909082 0.15762201
##  [32,] 0.05603233 0.790675998 0.15329170
##  [33,] 0.31745431 0.325826108 0.35671952
##  [34,] 0.06191007 0.772978961 0.16511101
##  [35,] 0.06534416 0.764871001 0.16978484
##  [36,] 0.02838226 0.875171602 0.09644618
##  [37,] 0.26485416 0.369036615 0.36610931
##  [38,] 0.43251681 0.222851023 0.34463227
##  [39,] 0.93523341 0.015699042 0.04906756
##  [40,] 0.03420401 0.858148217 0.10764785
##  [41,] 0.61248660 0.118873216 0.26864013
##  [42,] 0.89497852 0.027446751 0.07757461
##  [43,] 0.05805963 0.785699725 0.15624058
##  [44,] 0.11707424 0.637701213 0.24522457
##  [45,] 0.88873690 0.026693610 0.08456945
##  [46,] 0.03372378 0.854575515 0.11170069
##  [47,] 0.16674817 0.523912370 0.30933946
##  [48,] 0.97493219 0.005118142 0.01994963
##  [49,] 0.05803766 0.784838915 0.15712340
##  [50,] 0.76608884 0.072399117 0.16151200
##  [51,] 0.04409278 0.825088084 0.13081914
##  [52,] 0.96588844 0.007516040 0.02659543
##  [53,] 0.96442741 0.007861389 0.02771119
##  [54,] 0.91386598 0.021650214 0.06448379
##  [55,] 0.94819993 0.011324482 0.04047560
##  [56,] 0.73844004 0.066436991 0.19512299
##  [57,] 0.97943830 0.004080101 0.01648154
##  [58,] 0.95589417 0.009475024 0.03463081
##  [59,] 0.88735408 0.030357054 0.08228882
##  [60,] 0.87929350 0.034774452 0.08593202
##  [61,] 0.03587139 0.850387990 0.11374062
##  [62,] 0.05729704 0.789629161 0.15307382
##  [63,] 0.87906086 0.031108413 0.08983071
##  [64,] 0.06198987 0.769804299 0.16820592
##  [65,] 0.95099211 0.011686330 0.03732161
##  [66,] 0.05029160 0.805737555 0.14397085
##  [67,] 0.03420401 0.858148217 0.10764785
##  [68,] 0.50633574 0.167349130 0.32631516
##  [69,] 0.76481807 0.073198281 0.16198358
##  [70,] 0.92026961 0.019914243 0.05981617
##  [71,] 0.68456936 0.104777932 0.21065275
##  [72,] 0.94746661 0.012643692 0.03988962
##  [73,] 0.56940925 0.142874703 0.28771603
##  [74,] 0.90633512 0.022936849 0.07072805
##  [75,] 0.14855078 0.550868988 0.30058014
##  [76,] 0.94504309 0.012951720 0.04200512
##  [77,] 0.33087116 0.288887620 0.38024122
##  [78,] 0.35178947 0.291038156 0.35717237
##  [79,] 0.05188688 0.801872432 0.14624068
##  [80,] 0.07640111 0.729484916 0.19411406
##  [81,] 0.16926853 0.521955132 0.30877629
##  [82,] 0.95286143 0.010137549 0.03700102
##  [83,] 0.97495812 0.005120956 0.01992091
##  [84,] 0.29143119 0.338600755 0.36996797
##  [85,] 0.05011770 0.806323886 0.14355843
##  [86,] 0.06483519 0.766276062 0.16888881
##  [87,] 0.05944780 0.780880988 0.15967123
##  [88,] 0.05432448 0.795523465 0.15015204
##  [89,] 0.91746360 0.020890139 0.06164625
##  [90,] 0.93316072 0.014883612 0.05195569
##  [91,] 0.47389454 0.191995010 0.33411053
##  [92,] 0.05121505 0.803947389 0.14483756
##  [93,] 0.79826093 0.058594450 0.14314465
##  [94,] 0.68785042 0.090500720 0.22164892
##  [95,] 0.82125819 0.054322682 0.12441915
##  [96,] 0.95407909 0.010249035 0.03567187
##  [97,] 0.05904090 0.783161342 0.15779774
##  [98,] 0.51876068 0.170670703 0.31056857
##  [99,] 0.64437485 0.124427132 0.23119792
## [100,] 0.15706590 0.537996054 0.30493799
## [101,] 0.89267653 0.028202707 0.07912076
## [102,] 0.26123932 0.364885002 0.37387568
## [103,] 0.09082982 0.698524654 0.21064548
## [104,] 0.03545587 0.851317763 0.11322628
## [105,] 0.04372275 0.821913421 0.13436382
## [106,] 0.80073398 0.056968037 0.14229794
## [107,] 0.91150552 0.022340013 0.06615441
## [108,] 0.06851622 0.743815362 0.18766844
## [109,] 0.83444041 0.043688141 0.12187138
## [110,] 0.72679126 0.079977900 0.19323081
## [111,] 0.90992177 0.022378117 0.06770010
## [112,] 0.94054461 0.012840231 0.04661509
## [113,] 0.97565991 0.004839099 0.01950097
## [114,] 0.91718090 0.020713670 0.06210540
## [115,] 0.98708409 0.002231417 0.01068456
## [116,] 0.08241912 0.709093332 0.20848754
## [117,] 0.13192356 0.578998804 0.28907767
## [118,] 0.06681291 0.760834217 0.17235291
## [119,] 0.85173947 0.039359000 0.10890158
## [120,] 0.83432657 0.049126290 0.11654712
## [121,] 0.50193965 0.174716428 0.32334396
## [122,] 0.88090634 0.030556876 0.08853671
## [123,] 0.57671386 0.141602650 0.28168344
## [124,] 0.03753652 0.846849918 0.11561356
## [125,] 0.47781041 0.194046825 0.32814276
## [126,] 0.05421940 0.795294583 0.15048608
## [127,] 0.04107779 0.832982421 0.12593977
## [128,] 0.06587428 0.763712943 0.17041281
## [129,] 0.52440381 0.167928398 0.30766776
## [130,] 0.06258789 0.764198899 0.17321329
## [131,] 0.10621259 0.654716969 0.23907045
## [132,] 0.03437648 0.856076956 0.10954655
## [133,] 0.04032640 0.836452007 0.12322165
## [134,] 0.08407705 0.705464661 0.21045838
## [135,] 0.05773471 0.772924244 0.16934104
## [136,] 0.04225030 0.826045752 0.13170391
## [137,] 0.85143805 0.041710202 0.10685171
## [138,] 0.98501855 0.002803175 0.01217829
## [139,] 0.64406079 0.108678766 0.24726042
## [140,] 0.92678416 0.016281210 0.05693465
## [141,] 0.97903788 0.003943944 0.01701810
## [142,] 0.95150924 0.011078560 0.03741217
## [143,] 0.06271002 0.771336734 0.16595322
## [144,] 0.06240438 0.771324575 0.16627114
## [145,] 0.05050061 0.806346953 0.14315245
## [146,] 0.89642566 0.027822861 0.07575145
## [147,] 0.95042652 0.011275707 0.03829780
## [148,] 0.03241682 0.861085415 0.10649778
## [149,] 0.32020891 0.309010953 0.37078017
## [150,] 0.07142887 0.742034733 0.18653634
## [151,] 0.80784690 0.055161811 0.13699131
## [152,] 0.95438337 0.010064736 0.03555186
## [153,] 0.96756607 0.006873396 0.02556053
## [154,] 0.93873090 0.014361630 0.04690751
## [155,] 0.05603233 0.790675998 0.15329170
## [156,] 0.10754167 0.629429519 0.26302883
## [157,] 0.04106361 0.829788566 0.12914780
## [158,] 0.98501855 0.002803175 0.01217829
## [159,] 0.26446727 0.370212466 0.36532024
## [160,] 0.87227976 0.031874951 0.09584527
## [161,] 0.03903387 0.839769781 0.12119640
## [162,] 0.35307735 0.271113724 0.37580898
## [163,] 0.66223431 0.099781215 0.23798448
## [164,] 0.45525816 0.203968540 0.34077331
## [165,] 0.09325892 0.688320577 0.21842052
## [166,] 0.76695347 0.061693773 0.17135279
## [167,] 0.07646185 0.719296932 0.20424122
## [168,] 0.95278358 0.009845847 0.03737048
## [169,] 0.98024356 0.003729756 0.01602663
## [170,] 0.81424671 0.051936794 0.13381653
## [171,] 0.96099281 0.007952100 0.03105505
## [172,] 0.97099239 0.006094778 0.02291284
## [173,] 0.69129688 0.092487343 0.21621588
## [174,] 0.91871524 0.019893153 0.06139160
## [175,] 0.04940891 0.809282780 0.14130828
## [176,] 0.90142053 0.024693431 0.07388597
## [177,] 0.98004740 0.003877451 0.01607515
## [178,] 0.15427318 0.540596008 0.30513087
## [179,] 0.96711826 0.006887421 0.02599432
## [180,] 0.68737590 0.093909077 0.21871510
## [181,] 0.97718018 0.004283469 0.01853642
## [182,] 0.53167158 0.157389462 0.31093892
## [183,] 0.97520882 0.004920706 0.01987044
## [184,] 0.93620640 0.015036616 0.04875700
## [185,] 0.95231676 0.011279997 0.03640324
## [186,] 0.93843377 0.013238087 0.04832807
## [187,] 0.79623574 0.063736953 0.14002730
## [188,] 0.68497968 0.091219701 0.22380055
## [189,] 0.94879448 0.011454031 0.03975153
## [190,] 0.58811730 0.126894385 0.28498837
## [191,] 0.96884000 0.005954823 0.02520519
## [192,] 0.91916090 0.018425966 0.06241319
## [193,] 0.88685650 0.028262135 0.08488135
## [194,] 0.96328264 0.007635218 0.02908214
## [195,] 0.49458250 0.184186324 0.32123119
## [196,] 0.97986287 0.003823689 0.01631335
## [197,] 0.97377974 0.005076406 0.02114379
## [198,] 0.68906003 0.091210626 0.21972932
## [199,] 0.83209461 0.044903673 0.12300169
## [200,] 0.19732474 0.455269337 0.34740588
## [201,] 0.15117693 0.558091640 0.29073143
## [202,] 0.95773792 0.009459726 0.03280229
## [203,] 0.89230192 0.025660075 0.08203796
## [204,] 0.05989151 0.779480040 0.16062844
## [205,] 0.86182249 0.037327666 0.10084983
## [206,] 0.54107141 0.147433981 0.31149456
## [207,] 0.91414362 0.020263538 0.06559277
## [208,] 0.09860572 0.660806954 0.24058731
## [209,] 0.80721384 0.057694744 0.13509142
## [210,] 0.07590569 0.734757185 0.18933709
## [211,] 0.74268824 0.075504676 0.18180707
## [212,] 0.86486238 0.038512848 0.09662472
## [213,] 0.76713449 0.073451325 0.15941426
## [214,] 0.07165217 0.744758904 0.18358894
## [215,] 0.10347141 0.640215039 0.25631353
## [216,] 0.70390850 0.082738385 0.21335311
## [217,] 0.96354419 0.008028171 0.02842762
## [218,] 0.96342856 0.007825783 0.02874573
## [219,] 0.95076799 0.010804094 0.03842793
## [220,] 0.92197317 0.019234611 0.05879223
## [221,] 0.05562793 0.791793346 0.15257871
## [222,] 0.04847729 0.811361551 0.14016111
## [223,] 0.96701229 0.007083724 0.02590398
## [224,] 0.90312099 0.024709480 0.07216955
## [225,] 0.13278459 0.595264733 0.27195069
## [226,] 0.97599524 0.004957635 0.01904701
## [227,] 0.96110392 0.008418909 0.03047721
## [228,] 0.96037292 0.008883843 0.03074320
## [229,] 0.96777916 0.006300359 0.02592051
## [230,] 0.58976394 0.148165181 0.26207092
## [231,] 0.92734027 0.016274257 0.05638543
## [232,] 0.06810968 0.757508218 0.17438208
## [233,] 0.04321657 0.827462196 0.12932120
## [234,] 0.36456236 0.273700923 0.36173666
## [235,] 0.06117649 0.776775181 0.16204832
## [236,] 0.96825403 0.006443227 0.02530273
## [237,] 0.10747492 0.650814593 0.24171057
## [238,] 0.29303601 0.333152384 0.37381157
## [239,] 0.46909046 0.193574190 0.33733538
## [240,] 0.97884768 0.004136492 0.01701585
## [241,] 0.92886978 0.016908772 0.05422143
## [242,] 0.29575309 0.333727926 0.37051901
## [243,] 0.06167687 0.767811775 0.17051136
## [244,] 0.08470482 0.688258648 0.22703651
## [245,] 0.10206880 0.655895948 0.24203530
## [246,] 0.12897336 0.578347862 0.29267886
## [247,] 0.30969241 0.332556725 0.35775086
## [248,] 0.12147810 0.617347777 0.26117414
## [249,] 0.88689464 0.028877057 0.08422831
## [250,] 0.53581685 0.160801440 0.30338171
## [251,] 0.95864177 0.008977291 0.03238095
## [252,] 0.21364881 0.423230767 0.36312047
## [253,] 0.83635014 0.043814380 0.11983545
## [254,] 0.92860264 0.015931038 0.05546640
## [255,] 0.15211137 0.551918209 0.29597038
## [256,] 0.92954570 0.017278196 0.05317608
## [257,] 0.05685348 0.789347470 0.15379901
## [258,] 0.19894490 0.474773347 0.32628173
## [259,] 0.05462937 0.793913841 0.15145674
## [260,] 0.18392149 0.488638580 0.32743993
## [261,] 0.92321253 0.019540492 0.05724703
## [262,] 0.54887938 0.147987291 0.30313331
## [263,] 0.07065501 0.750805736 0.17853931
## [264,] 0.06608067 0.763142586 0.17077674
## [265,] 0.97045338 0.005875469 0.02367109
## [266,] 0.90689546 0.024678092 0.06842644
## [267,] 0.26659298 0.391209573 0.34219745
## [268,] 0.19138709 0.482491612 0.32612124
## [269,] 0.93835717 0.014930250 0.04671257
## [270,] 0.09714130 0.674413681 0.22844501
## [271,] 0.31298131 0.307003230 0.38001543
## [272,] 0.95721531 0.009106952 0.03367775
## [273,] 0.36456236 0.273700923 0.36173666
## [274,] 0.91364634 0.020644134 0.06570964
## [275,] 0.03420401 0.858148217 0.10764785
## [276,] 0.96405864 0.007381370 0.02855999
## [277,] 0.94610596 0.012079893 0.04181415
## [278,] 0.98199952 0.003409788 0.01459069
## [279,] 0.49009034 0.174825251 0.33508441
## [280,] 0.90722489 0.021520734 0.07125442
## [281,] 0.13278459 0.595264733 0.27195069
## [282,] 0.54628336 0.148806125 0.30491051
## [283,] 0.17241156 0.518478572 0.30910984
## [284,] 0.05297168 0.798985302 0.14804304
## [285,] 0.84179890 0.043252859 0.11494818
## [286,] 0.97197545 0.005771175 0.02225335
## [287,] 0.95702672 0.009062407 0.03391082
## [288,] 0.40638071 0.225596264 0.36802304
## [289,] 0.47660562 0.191025913 0.33236843
## [290,] 0.97416770 0.005274174 0.02055808
## [291,] 0.89612788 0.024614876 0.07925721
## [292,] 0.06299096 0.771097779 0.16591123
## [293,] 0.91529995 0.020463567 0.06423645
## [294,] 0.20996058 0.428381771 0.36165768
## [295,] 0.52525800 0.161447957 0.31329402
## [296,] 0.86656290 0.036994971 0.09644218
## [297,] 0.89870715 0.026782338 0.07451051
## [298,] 0.95567548 0.009471050 0.03485339
## [299,] 0.83821577 0.049405303 0.11237897
## [300,] 0.06001101 0.779592574 0.16039637
## [301,] 0.04970520 0.807805896 0.14248885
## [302,] 0.95268571 0.010748335 0.03656607
## [303,] 0.49528849 0.169246241 0.33546525
## [304,] 0.85984939 0.037872247 0.10227837
## [305,] 0.65920597 0.099801496 0.24099261
## [306,] 0.96735942 0.006388119 0.02625239
## [307,] 0.26257101 0.392502129 0.34492686
## [308,] 0.93186677 0.016134061 0.05199917
## [309,] 0.26557574 0.358010650 0.37641361
## [310,] 0.89394766 0.028565232 0.07748715
## [311,] 0.83371663 0.046627268 0.11965606
## [312,] 0.82044983 0.048684910 0.13086523
## [313,] 0.42792645 0.218553662 0.35351989
## [314,] 0.05759988 0.782221973 0.16017808
## [315,] 0.09150262 0.690644443 0.21785296
## [316,] 0.05101869 0.804683030 0.14429834
## [317,] 0.06710169 0.756053507 0.17684481
## [318,] 0.53212148 0.159509912 0.30836856
## [319,] 0.05135053 0.803665876 0.14498366
## [320,] 0.81984371 0.051593013 0.12856324
## [321,] 0.08111332 0.718882024 0.20000459
## [322,] 0.13323626 0.589834690 0.27692908
## [323,] 0.97304630 0.005453612 0.02150011
## [324,] 0.82979858 0.046176951 0.12402452
## [325,] 0.10505842 0.657241046 0.23770057
## [326,] 0.05833515 0.776710033 0.16495484
## [327,] 0.04530305 0.816210628 0.13848637
## [328,] 0.97149503 0.006027434 0.02247753
## [329,] 0.05982462 0.772558272 0.16761701
## [330,] 0.98335749 0.003074897 0.01356755
## [331,] 0.97865218 0.004254560 0.01709337
## [332,] 0.04159893 0.830530643 0.12787043
## [333,] 0.04972833 0.809683502 0.14058809
## [334,] 0.18534085 0.491042703 0.32361645
## [335,] 0.10099786 0.653747678 0.24525441
## [336,] 0.06732199 0.760612786 0.17206524
## [337,] 0.78200448 0.068468690 0.14952685
## [338,] 0.88602966 0.029991094 0.08397922
## [339,] 0.06160346 0.770453632 0.16794297
## [340,] 0.97727352 0.004579589 0.01814689
## [341,] 0.03420401 0.858148217 0.10764785
## [342,] 0.97309285 0.005304361 0.02160276
## [343,] 0.14407152 0.569886744 0.28604174
## [344,] 0.91600847 0.021777194 0.06221430
## [345,] 0.11617180 0.629062414 0.25476581
## [346,] 0.83198404 0.046790119 0.12122583
## [347,] 0.93256545 0.016799381 0.05063519
## [348,] 0.98277354 0.003170471 0.01405603
## [349,] 0.87532109 0.031599276 0.09307965
## [350,] 0.33271217 0.302682430 0.36460534
## [351,] 0.44217658 0.218422756 0.33940071
## [352,] 0.08174567 0.720427930 0.19782637
## [353,] 0.06400537 0.768355727 0.16763894
## [354,] 0.03295372 0.858920217 0.10812605
## [355,] 0.97738862 0.004477987 0.01813336
## [356,] 0.21115756 0.452836156 0.33600622
## [357,] 0.11785899 0.612885058 0.26925594
## [358,] 0.05284495 0.792083800 0.15507123
## [359,] 0.68078077 0.095142290 0.22407694
## [360,] 0.25861832 0.357169390 0.38421232
## [361,] 0.10104844 0.664725244 0.23422632
## [362,] 0.83399594 0.044537198 0.12146681
## [363,] 0.07027215 0.751647890 0.17807992
## [364,] 0.02426977 0.890237689 0.08549261
## [365,] 0.05866184 0.781929314 0.15940882
## [366,] 0.47146723 0.186498538 0.34203422
## [367,] 0.78249091 0.064021222 0.15348779
## [368,] 0.90365756 0.024018466 0.07232398
## [369,] 0.07978043 0.721809626 0.19840994
## [370,] 0.87570781 0.034576606 0.08971566
## [371,] 0.04947762 0.803056240 0.14746617
## [372,] 0.95103770 0.011890335 0.03707203
## [373,] 0.86248875 0.036616787 0.10089438
## [374,] 0.91583431 0.019036263 0.06512951
## [375,] 0.90114814 0.024997443 0.07385444
## [376,] 0.92775267 0.016483542 0.05576380
## [377,] 0.05262310 0.794108033 0.15326886
## [378,] 0.94229990 0.014018913 0.04368126
## [379,] 0.97475320 0.005044579 0.02020223
## [380,] 0.07500958 0.739305079 0.18568535
## [381,] 0.05668053 0.788589358 0.15473010
## [382,] 0.12499149 0.623634934 0.25137359
## [383,] 0.20391501 0.458307266 0.33777767
## [384,] 0.93608093 0.014809390 0.04910963
## [385,] 0.94606215 0.012658544 0.04127925
## [386,] 0.07032034 0.752059162 0.17762046
## [387,] 0.92378151 0.017526276 0.05869225
## [388,] 0.93197364 0.015692528 0.05233380
## [389,] 0.96138972 0.008525660 0.03008454
## [390,] 0.92113268 0.018645380 0.06022201
## [391,] 0.05750903 0.786397099 0.15609391
## [392,] 0.13987723 0.582137465 0.27798533
## [393,] 0.51882583 0.167262435 0.31391174
## [394,] 0.02488283 0.887896657 0.08722046
## [395,] 0.07100151 0.746595740 0.18240277
## [396,] 0.12556706 0.600136459 0.27429646
## [397,] 0.21805121 0.405737847 0.37621096
## [398,] 0.15713839 0.550893247 0.29196835
## [399,] 0.05928951 0.782384515 0.15832594
## [400,] 0.93549919 0.015740285 0.04876054
## [401,] 0.09653980 0.675755978 0.22770418
## [402,] 0.06508621 0.759433389 0.17548041
## [403,] 0.95025069 0.011603232 0.03814600
## [404,] 0.92949688 0.015901580 0.05460154
## [405,] 0.79756385 0.060165524 0.14227071
## [406,] 0.26855698 0.366704822 0.36473820
## [407,] 0.60886884 0.123526700 0.26760453
## [408,] 0.13117367 0.598959208 0.26986712
## [409,] 0.88271534 0.030965984 0.08631875
## [410,] 0.04904966 0.806116045 0.14483424
## [411,] 0.49901846 0.183479592 0.31750199
## [412,] 0.91656005 0.018818477 0.06462147
## [413,] 0.05777095 0.785876751 0.15635228
## [414,] 0.81966072 0.050258450 0.13008083
## [415,] 0.88980639 0.026817525 0.08337609
## [416,] 0.83735615 0.044084046 0.11855981
## [417,] 0.92984802 0.016629517 0.05352245
## [418,] 0.96199167 0.008596919 0.02941142
## [419,] 0.95656770 0.009824582 0.03360762
## [420,] 0.82610017 0.048291426 0.12560835
## [421,] 0.19805160 0.461325586 0.34062272
## [422,] 0.63745791 0.109067202 0.25347489
## [423,] 0.92502654 0.016898027 0.05807541
## [424,] 0.05482676 0.791847169 0.15332603
## [425,] 0.07042449 0.743868828 0.18570668
## [426,] 0.97829652 0.004157653 0.01754579
## [427,] 0.94779336 0.012098218 0.04010848
## [428,] 0.03187490 0.864202440 0.10392267
## [429,] 0.33933192 0.298156619 0.36251140
## [430,] 0.90591568 0.024843995 0.06924033
## [431,] 0.95599276 0.009434144 0.03457318
## [432,] 0.91299450 0.021387812 0.06561759
## [433,] 0.41044024 0.219769195 0.36979055
## [434,] 0.93984455 0.014341075 0.04581437
## [435,] 0.02426977 0.890237689 0.08549261
## [436,] 0.06039292 0.778386712 0.16122045
## [437,] 0.21532165 0.425484240 0.35919410
## [438,] 0.81385833 0.056922138 0.12921953
## [439,] 0.13628027 0.566992581 0.29672715
## [440,] 0.86714804 0.035723750 0.09712817
## [441,] 0.07278850 0.744715095 0.18249637
## [442,] 0.94383591 0.012557089 0.04360693
## [443,] 0.19518174 0.447806180 0.35701203
## [444,] 0.92708123 0.018506611 0.05441221
## [445,] 0.17758125 0.518945873 0.30347288
## [446,] 0.05712799 0.786751568 0.15612048
## [447,] 0.05896920 0.782190681 0.15884008
## [448,] 0.06610660 0.762304068 0.17158937
## [449,] 0.96510923 0.006878498 0.02801228
## [450,] 0.96219140 0.007542991 0.03026551
## [451,] 0.56553876 0.137934983 0.29652619
## [452,] 0.94996953 0.010900833 0.03912957
## [453,] 0.95658505 0.009507996 0.03390693
## [454,] 0.94746661 0.012643692 0.03988962
## [455,] 0.05990461 0.778946638 0.16114876
## [456,] 0.42486024 0.220823407 0.35431638
## [457,] 0.03882510 0.833925784 0.12724911
## [458,] 0.45213768 0.203209355 0.34465292
## [459,] 0.96289438 0.007340475 0.02976511
## [460,] 0.41631800 0.237659350 0.34602267
## [461,] 0.93532538 0.015493263 0.04918132
## [462,] 0.96511102 0.006809544 0.02807934
## [463,] 0.73036265 0.093218580 0.17641875
## [464,] 0.94396871 0.011682231 0.04434904
## [465,] 0.14119220 0.567265213 0.29154253
## [466,] 0.97786194 0.004224677 0.01791346
## [467,] 0.17041543 0.503663480 0.32592112
## [468,] 0.46919543 0.190036729 0.34076783
## [469,] 0.95733571 0.008625647 0.03403865
## [470,] 0.78902334 0.064149715 0.14682697
## [471,] 0.08221091 0.720062315 0.19772671
## [472,] 0.96266907 0.007318796 0.03001211
## [473,] 0.83692956 0.042753708 0.12031671
## [474,] 0.88912773 0.027826661 0.08304560
## [475,] 0.78308356 0.068443842 0.14847264
## [476,] 0.37827036 0.248253018 0.37347665
## [477,] 0.40733558 0.243495122 0.34916925
## [478,] 0.50700635 0.171764314 0.32122931
## [479,] 0.97328126 0.005441194 0.02127757
## [480,] 0.80043918 0.058467861 0.14109293
## [481,] 0.63119680 0.112174816 0.25662833
## [482,] 0.95853561 0.008320696 0.03314373
## [483,] 0.91908598 0.019005224 0.06190880
## [484,] 0.52353340 0.170933530 0.30553311
## [485,] 0.52353340 0.170933530 0.30553311
## [486,] 0.97568011 0.004941176 0.01937861
## [487,] 0.86300671 0.038968008 0.09802534
## [488,] 0.92429912 0.019142652 0.05655817
## [489,] 0.94291592 0.013806728 0.04327733
## [490,] 0.93748337 0.014567155 0.04794949
## [491,] 0.87200081 0.033644076 0.09435513
## [492,] 0.05671617 0.774334490 0.16894931
## [493,] 0.87953675 0.029226782 0.09123655
## [494,] 0.23026446 0.436654627 0.33308089
## [495,] 0.45327151 0.205263555 0.34146494
## [496,] 0.40457615 0.244292393 0.35113147
## [497,] 0.14612924 0.559931099 0.29393962
## [498,] 0.45787457 0.191835895 0.35028958
## [499,] 0.15869501 0.511123478 0.33018151
## [500,] 0.86792225 0.036815196 0.09526255
## [501,] 0.68690199 0.097067386 0.21603061
## [502,] 0.41354558 0.224097505 0.36235690
## [503,] 0.84945065 0.041213065 0.10933627
## [504,] 0.83612841 0.045300182 0.11857139
## [505,] 0.89569765 0.025105067 0.07919728
## [506,] 0.52941197 0.167124361 0.30346373
## [507,] 0.05367119 0.797468126 0.14886066
## [508,] 0.04899712 0.805886805 0.14511609
## [509,] 0.10851382 0.633439660 0.25804648
## [510,] 0.92234033 0.017993813 0.05966590
## [511,] 0.97810042 0.004064195 0.01783534
## [512,] 0.84648073 0.041401405 0.11211782
## [513,] 0.04910035 0.810163498 0.14073618
## [514,] 0.06348374 0.769548357 0.16696797
## [515,] 0.91858196 0.019744799 0.06167329
## [516,] 0.92653161 0.019194486 0.05427387
## [517,] 0.09500225 0.682660878 0.22233690
## [518,] 0.35798198 0.291539848 0.35047820
## [519,] 0.97787058 0.004450853 0.01767861
## [520,] 0.69053602 0.091274254 0.21818970
## [521,] 0.97727352 0.004579589 0.01814689
## [522,] 0.11995857 0.620484054 0.25955734
## [523,] 0.12728505 0.602874398 0.26984060
## [524,] 0.96472192 0.007259128 0.02801898
## [525,] 0.03685611 0.847656965 0.11548693
## [526,] 0.15998541 0.531499267 0.30851528
## [527,] 0.94883192 0.010986298 0.04018167
## [528,] 0.65515572 0.100037977 0.24480635
## [529,] 0.03685611 0.847656965 0.11548693
## [530,] 0.89642566 0.027822861 0.07575145
## [531,] 0.09052230 0.686963797 0.22251394
## [532,] 0.79463065 0.063158475 0.14221090
## [533,] 0.05600068 0.790937126 0.15306222
## [534,] 0.05072863 0.794938266 0.15433319
## [535,] 0.89666855 0.028423004 0.07490839
## [536,] 0.81747550 0.050493319 0.13203122
## [537,] 0.17288597 0.515207887 0.31190613
## [538,] 0.06137709 0.765061557 0.17356130
## [539,] 0.73202479 0.079145379 0.18882988
## [540,] 0.94322443 0.013890407 0.04288518
## [541,] 0.15682143 0.539668083 0.30351052
## [542,] 0.90676939 0.021997765 0.07123285
## [543,] 0.06392825 0.769262135 0.16680966
## [544,] 0.84063679 0.042035386 0.11732776
## [545,] 0.96376485 0.007883254 0.02835189
## [546,] 0.02986891 0.870530725 0.09960040
## [547,] 0.66067153 0.109778255 0.22955020
## [548,] 0.06175140 0.764411211 0.17383744
## [549,] 0.05928951 0.782384515 0.15832594
## [550,] 0.06567402 0.763131380 0.17119460
## [551,] 0.52203053 0.156331256 0.32163820
## [552,] 0.96293366 0.008044284 0.02902210
## [553,] 0.16991374 0.498349637 0.33173665
## [554,] 0.03522400 0.852728128 0.11204790
## [555,] 0.22541736 0.447568208 0.32701442
## [556,] 0.63954747 0.104590297 0.25586221
## [557,] 0.05472682 0.792481601 0.15279162
## [558,] 0.95103770 0.011890335 0.03707203
## [559,] 0.02426977 0.890237689 0.08549261
## [560,] 0.07831384 0.728496790 0.19318935
## [561,] 0.05050061 0.806346953 0.14315245
## [562,] 0.02426977 0.890237689 0.08549261
## [563,] 0.94030535 0.013011727 0.04668285
## [564,] 0.66921204 0.093253687 0.23753420
## [565,] 0.74912196 0.082734138 0.16814388
## [566,] 0.73987693 0.086952940 0.17317009
## [567,] 0.61746258 0.114602089 0.26793534
## [568,] 0.64168620 0.112728953 0.24558486
## [569,] 0.31310943 0.322626293 0.36426425
## [570,] 0.97378141 0.005266273 0.02095229
## [571,] 0.05106838 0.804792702 0.14413886
## [572,] 0.05860455 0.781674504 0.15972096
## [573,] 0.95600182 0.010209336 0.03378882
## [574,] 0.96013564 0.009132550 0.03073188
## [575,] 0.04054197 0.834373951 0.12508409
## [576,] 0.13070963 0.573240936 0.29604939
## [577,] 0.05735322 0.786543250 0.15610348
## [578,] 0.06844985 0.755849600 0.17570058
## [579,] 0.94346398 0.013587980 0.04294802
## [580,] 0.93536866 0.016448582 0.04818273
## [581,] 0.05481098 0.794815838 0.15037321
## [582,] 0.21609934 0.413658530 0.37024209
## [583,] 0.92963308 0.018033158 0.05233385
## [584,] 0.50374013 0.168186843 0.32807308
## [585,] 0.09171104 0.681463301 0.22682567
## [586,] 0.08278850 0.713710725 0.20350081
## [587,] 0.78536630 0.059705533 0.15492824
## [588,] 0.13481233 0.576710880 0.28847682
## [589,] 0.44475314 0.203940034 0.35130689
## [590,] 0.02873880 0.874687552 0.09657359
## [591,] 0.66637218 0.099681720 0.23394607
## [592,] 0.95491648 0.009042631 0.03604098
## [593,] 0.15079960 0.537463248 0.31173715
## [594,] 0.07133536 0.742563307 0.18610132
## [595,] 0.08393130 0.709591448 0.20647722
## [596,] 0.89267653 0.028202707 0.07912076
## [597,] 0.98409581 0.002911736 0.01299250
## [598,] 0.97602296 0.004976777 0.01900020
## [599,] 0.05093630 0.798435748 0.15062794
## [600,] 0.05928951 0.782384515 0.15832594
## [601,] 0.03942521 0.839820981 0.12075383
## [602,] 0.64629722 0.106526166 0.24717665
## [603,] 0.02925827 0.870544076 0.10019769
## [604,] 0.15322642 0.525574267 0.32119933
## [605,] 0.25006625 0.382649064 0.36728472
## [606,] 0.89740872 0.024066208 0.07852510
## [607,] 0.95096731 0.010508955 0.03852377
## [608,] 0.79433411 0.052082721 0.15358329
## [609,] 0.05518682 0.794482231 0.15033095
## [610,] 0.93548936 0.015517578 0.04899304
## [611,] 0.92931443 0.016447829 0.05423778
## [612,] 0.03315178 0.859264553 0.10758365
## [613,] 0.97291058 0.005822538 0.02126693
## [614,] 0.05978516 0.780018687 0.16019610
## [615,] 0.04063188 0.832220912 0.12714717
## [616,] 0.05198628 0.797630489 0.15038317
## [617,] 0.86007005 0.039336428 0.10059352
## [618,] 0.05928951 0.782384515 0.15832594
## [619,] 0.09890887 0.671146393 0.22994471
## [620,] 0.35224092 0.291928530 0.35583046
## [621,] 0.90618068 0.023436323 0.07038302
## [622,] 0.08095884 0.724420249 0.19462092
## [623,] 0.85308516 0.042448800 0.10446607
## [624,] 0.12008181 0.619516671 0.26040146
## [625,] 0.97704679 0.004702559 0.01825060
## [626,] 0.24189654 0.389414608 0.36868885
## [627,] 0.88893986 0.028630054 0.08243003
## [628,] 0.91682273 0.020703265 0.06247401
## [629,] 0.05812177 0.784294844 0.15758340
## [630,] 0.67852789 0.104027741 0.21744438
## [631,] 0.97989070 0.003949326 0.01616006
## [632,] 0.96031690 0.008844908 0.03083826
## [633,] 0.09781562 0.674170971 0.22801341
## [634,] 0.77058995 0.075586706 0.15382347
## [635,] 0.78068876 0.061090592 0.15822057
## [636,] 0.98202753 0.003426761 0.01454562
## [637,] 0.93671072 0.014759242 0.04852996
## [638,] 0.58083516 0.133519098 0.28564569
## [639,] 0.03318805 0.856985807 0.10982617
## [640,] 0.57690555 0.130454093 0.29264030
## [641,] 0.08337699 0.711948216 0.20467484

pred_class <- apply(pred, 1, which.max)
actual_class <- apply(y_test, 1, which.max)

# =========================
# CONFUSION MATRIX
# =========================
pred_factor <- factor(pred_class, levels = c(1,2,3),
                      labels = c("Negatif","Netral","Positif"))

actual_factor <- factor(actual_class, levels = c(1,2,3),
                        labels = c("Negatif","Netral","Positif"))

confusionMatrix(pred_factor, actual_factor)

## Confusion Matrix and Statistics
## 
##           Reference
## Prediction Negatif Netral Positif
##    Negatif     301     35      37
##    Netral       39    164      47
##    Positif       8      5       5
## 
## Overall Statistics
##                                           
##                Accuracy : 0.7332          
##                  95% CI : (0.6972, 0.7671)
##     No Information Rate : 0.5429          
##     P-Value [Acc > NIR] : < 2.2e-16       
##                                           
##                   Kappa : 0.5202          
##                                           
##  Mcnemar's Test P-Value : 1.995e-11       
## 
## Statistics by Class:
## 
##                      Class: Negatif Class: Netral Class: Positif
## Sensitivity                  0.8649        0.8039        0.05618
## Specificity                  0.7543        0.8032        0.97645
## Pos Pred Value               0.8070        0.6560        0.27778
## Neg Pred Value               0.8246        0.8977        0.86517
## Prevalence                   0.5429        0.3183        0.13885
## Detection Rate               0.4696        0.2559        0.00780
## Detection Prevalence         0.5819        0.3900        0.02808
## Balanced Accuracy            0.8096        0.8036        0.51631

# =========================
# HEATMAP CONFUSION MATRIX
# =========================
cm_table <- table(Prediksi = pred_factor, Aktual = actual_factor)
cm_df <- as.data.frame(cm_table)

ggplot(cm_df, aes(x = Aktual, y = Prediksi, fill = Freq)) +
  geom_tile(color = "white") +
  geom_text(aes(label = Freq), size = 5, color = "white", fontface = "bold") +
  scale_fill_gradient(low = "#ff9999", high = "#660000") +
  theme_minimal() +
  labs(
    x = "Aktual",
    y = "Prediksi"
  )

# =========================
# WORDCLOUD
# =========================
text_all <- paste(df_final$text_clean, collapse = " ")

corpus <- Corpus(VectorSource(text_all))
tdm <- TermDocumentMatrix(corpus)
m <- as.matrix(tdm)

freq <- sort(rowSums(m), decreasing = TRUE)
df_word <- data.frame(word = names(freq), freq = freq)

png("wordcloud.png", width = 1600, height = 1000, res = 150)

par(bg = "white")
par(mar = c(1,1,1,1))
par(font = 2) 

# Warna gradasi merah
warna_merah <- colorRampPalette(c(
  "#ff6666",
  "#ff3333",
  "#cc0000",
  "#990000",
  "#660000"
))

wordcloud2(df_word,
           size =  0.7,
           color = "random-light",
           backgroundColor = "black")

dev.off()

## png 
##   2