DataMiningClassifier | text classifier based on Decision Trees ID3 | Machine Learning library

function train(; kws...)
args = Args(; kws...) # collect options in a stuct for convinience

if CUDA.functional() && args.use_cuda
    @info "Training on CUDA GPU"
    CUDA.allwoscalar(false)
    device = gpu
else
    @info "Training on CPU"
    device = cpu
end

# Prepare datasets
x_train, x_test, y_train, y_test = getdata(args, device)

# Create DataLoaders (mini-batch iterators)
train_loader = DataLoader((x_train, y_train), batchsize=args.batchsize, shuffle=true)
test_loader = DataLoader((x_test, y_test), batchsize=args.batchsize)

# Construct model
model = build_model() |> device
ps = Flux.params(model) # model's trainable parameters

best_param = ps
if args.optimiser == "SGD"
    # Regular training step with SGD

elseif args.optimiser == "RSO"
    # Run RSO function and update ps
    best_param .= RSO(x_train, y_train, args.RSOupdate, model, args.batchsize, device)
end

function RSO(X,L,C,model, batch_size, device)
"""
model = convolutional model structure
X = Input data
L = labels
C = Number of rounds to update parameters
W = Weight set of layers
Wd = Weight tensors of layer d that generates an activation
wid = weight tensor that generates an activation aᵢ
wj = a weight in wid
"""

# Normalize input data to have zero mean and unit standard deviation
X .= (X .- sum(X))./std(X)
train_loader = DataLoader((X, L), batchsize=batch_size, shuffle=true)

#println("model = $(typeof(model))")

std_prep = []
σ_d = Float64[]
D = 1
for layer in model
    D += 1
    Wd = Flux.params(layer)
    # Initialize the weights of the network with Gaussian distribution
    for id in Wd
        wj = convert(Array{Float32, 4}, rand(Normal(0, sqrt(2/length(id))), (3,3,4,4)))
        id = wj
        append!(std_prep, vec(wj))
    end
    # Compute std of all elements in the weight tensor Wd
    push!(σ_d, std(std_prep))
end

W = Flux.params(model)

# Weight update
for _ in 1:C
    d = D
    while d > 0
        for id in 1:length(W[d])
            # Randomly sample change in weights from Gaussian distribution
            for j in 1:length(w[d][id])
                # Randomly sample mini-batch
                (x, l) = train_loader[rand(1:length(train_loader))]
                
                # Sample a weight from normal distribution
                ΔWj[d][id][j] = rand(Normal(0, σ_d[d]), 1)

                loss, acc = loss_and_accuracy(data_loader, model, device)
                W = argmin(F(x,l, W+ΔWj), F(x,l,W), F(x,l, W-ΔWj))
            end
        end
        d -= 1
    end
end

return W
end

predictions = np.argmax(trainer.test(test_x), axis=1)

# Confusion matrix and classification report.
print(classification_report(test_y, predictions))

            precision    recall  f1-score   support

          0       0.75      0.79      0.77      1000
          1       0.81      0.87      0.84      1000
          2       0.63      0.61      0.62      1000
          3       0.55      0.47      0.50      1000
          4       0.66      0.66      0.66      1000
          5       0.62      0.64      0.63      1000
          6       0.74      0.83      0.78      1000
          7       0.80      0.74      0.77      1000
          8       0.85      0.81      0.83      1000
          9       0.79      0.80      0.80      1000

avg / total       0.72      0.72      0.72     10000

from transformers import DistilBertForSequenceClassification, Trainer, TrainingArguments

training_args = TrainingArguments(
    output_dir='./results',          # output directory
    num_train_epochs=3,              # total number of training epochs
    per_device_train_batch_size=16,  # batch size per device during training
    per_device_eval_batch_size=64,   # batch size for evaluation
    warmup_steps=500,                # number of warmup steps for learning rate scheduler
    weight_decay=0.01,               # strength of weight decay
    logging_dir='./logs',            # directory for storing logs
    logging_steps=10,
)

model = DistilBertForSequenceClassification.from_pretrained("distilbert-base-uncased")

trainer = Trainer(
    model=model,                         # the instantiated 🤗 Transformers model to be trained
    args=training_args,                  # training arguments, defined above
    train_dataset=train_dataset,         # training dataset
    eval_dataset=val_dataset             # evaluation dataset
)

trainer.train()

from pathlib import Path

def read_imdb_split(split_dir):
    split_dir = Path(split_dir)
    texts = []
    labels = []
    for label_dir in ["pos", "neg"]:
        for text_file in (split_dir/label_dir).iterdir():
            texts.append(text_file.read_text())
            labels.append(0 if label_dir is "neg" else 1)

    return texts, labels

train_texts, train_labels = read_imdb_split('aclImdb/train')
test_texts, test_labels = read_imdb_split('aclImdb/test')

from sklearn.model_selection import train_test_split
train_texts, val_texts, train_labels, val_labels = train_test_split(train_texts, train_labels, test_size=.2)

from transformers import DistilBertTokenizerFast
tokenizer = DistilBertTokenizerFast.from_pretrained('distilbert-base-uncased')

train_encodings = tokenizer(train_texts, truncation=True, padding=True)
val_encodings = tokenizer(val_texts, truncation=True, padding=True)
test_encodings = tokenizer(test_texts, truncation=True, padding=True)

import torch

class IMDbDataset(torch.utils.data.Dataset):
    def __init__(self, encodings, labels):
        self.encodings = encodings
        self.labels = labels

    def __getitem__(self, idx):
        item = {key: torch.tensor(val[idx]) for key, val in self.encodings.items()}
        item['labels'] = torch.tensor(self.labels[idx])
        return item

    def __len__(self):
        return len(self.labels)

train_dataset = IMDbDataset(train_encodings, train_labels)
val_dataset = IMDbDataset(val_encodings, val_labels)
test_dataset = IMDbDataset(test_encodings, test_labels)

|    0   N/A  N/A      1047      G   /usr/lib/xorg/Xorg                168MiB |
|    0   N/A  N/A      5521      G   /usr/lib/xorg/Xorg                363MiB |
|    0   N/A  N/A      5637      G   /usr/bin/gnome-shell              161MiB |

from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score
baseline = LogisticRegression()
baseline.fit(X_train, y_train)
pred = baseline.predict(X_train)
print(accuracy_score(y_train, pred))

from sklearn.model_selection import cross_val_score, GridSearchCV, StratifiedKFold
X_val, X_test_val,y_val,y_test_val = train_test_split(X_train, y_train, test_size=0.3, random_state=42)
cv = StratifiedKFold(n_splits=5, random_state=0, shuffle=True)
parameters = [ ... ]
best_model = GridSearchCV(LogisticRegression(parameters,scoring='accuracy' ,cv=cv))
best_model.fit(X_val, y_val)
print(best_model.best_score_)

const brain = require('brain.js');

var net = new brain.NeuralNetwork();

net.train([
  { input: [0, 0], output: [0] },
  { input: [0, 1], output: [1] },
  { input: [1, 0], output: [1] },
  { input: [1, 1], output: [0] },
]);

var output = net.run([1, 0]); // [0.987]

console.log(output);

some_data[some_col].value_counts()
[OUTPUT]
color_white    11413
color_green     4544
color_black     1419
color_orang        3
Name: shirt_colors, dtype: int64

# Load the BERT Model
from sentence_transformers import SentenceTransformer
model = SentenceTransformer('bert-base-nli-mean-tokens')

# Setup a Corpus
# A corpus is a list with documents split by sentences.

sentences = ['Absence of sanity', 
             'Lack of saneness',
             'A man is eating food.',
             'A man is eating a piece of bread.',
             'The girl is carrying a baby.',
             'A man is riding a horse.',
             'A woman is playing violin.',
             'Two men pushed carts through the woods.',
             'A man is riding a white horse on an enclosed ground.',
             'A monkey is playing drums.',
             'A cheetah is running behind its prey.']

# Each sentence is encoded as a 1-D vector with 78 columns 
sentence_embeddings = model.encode(sentences) ### how to increase vector dimention 

print('Sample BERT embedding vector - length', len(sentence_embeddings[0]))

print('Sample BERT embedding vector - note includes negative values', sentence_embeddings[0])

+---------+-----+-----------+---------+--------+-----------+--------+---------+-------------+------------+
| user_id | age | car_price | car_age | income | education | gender | crashes | probability | true_labes |
+---------+-----+-----------+---------+--------+-----------+--------+---------+-------------+------------+
| 1       | 29  | 15600     | 3       | 20000  | 3         | 1      | 1       | 0.23        | 0          |
+---------+-----+-----------+---------+--------+-----------+--------+---------+-------------+------------+
| 2       | 41  | 43000     | 1       | 65000  | 2         | 0      | 1       | 0.1         | 0          |
+---------+-----+-----------+---------+--------+-----------+--------+---------+-------------+------------+
| 3       | 39  | 23500     | 5       | 43000  | 3         | 1      | 0       | 0.46        | 1          |
+---------+-----+-----------+---------+--------+-----------+--------+---------+-------------+------------+
| 4       | 19  | 12200     | 3       | 13000  | 1         | 1      | 0       | 0.34        | 1          |
+---------+-----+-----------+---------+--------+-----------+--------+---------+-------------+------------+
| 5       | 68  | 21900     | 2       | 31300  | 3         | 0      | 1       | 0.85        | 1          |
+---------+-----+-----------+---------+--------+-----------+--------+---------+-------------+------------+