train_classifier.py

import pickle
from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score
import numpy as np

# Function to pad or truncate sequences to a fixed length
def pad_sequences(sequences, maxlen):
    padded_sequences = np.zeros((len(sequences), maxlen))
    for i, seq in enumerate(sequences):
        if len(seq) > maxlen:
            padded_sequences[i, :] = seq[:maxlen]
        else:
            padded_sequences[i, :len(seq)] = seq
    return padded_sequences

data_dict = pickle.load(open('./data.pickle', 'rb'))

# Set the desired fixed length for all sequences
fixed_length = 100  # Adjust this value based on your data

data = pad_sequences(data_dict['data'], maxlen=fixed_length)
labels = np.asarray(data_dict['labels'])

x_train, x_test, y_train, y_test = train_test_split(data, labels, test_size=0.2, shuffle=True, stratify=labels)

model = RandomForestClassifier()
model.fit(x_train, y_train)
y_predict = model.predict(x_test)

score = accuracy_score(y_predict, y_test)
print('{}% of samples were classified correctly !'.format(score * 100))

f = open('model.p', 'wb')
pickle.dump({'model': model}, f)
f.close()