Различия Matlab и Python

scaler = StandardScaler().fit_transform(features)
train, test, train_labels, test_labels = train_test_split(scaler, labels, test_size=0.3, random_state=100)
 
svm = svm.SVC(kernel='rbf', gamma=1, C=1, cache_size=1024, max_iter=1000000)
model_svm = svm.fit(train, train_labels)
preds_svm = svm.predict(test)
acc_svm = accuracy_score(test_labels, preds_svm)
 
print(f'SVM accuracy is: {acc_svm * 100}')
 
with open('../../models/model.pkl', 'wb') as f:
    pickle.dump(model_svm, f)

    with open("models/model.pkl", "rb") as f:
        model = pickle.load(f)
 
    from sklearn.preprocessing import StandardScaler
 
    pred = model.predict(data.reshape(1, -1)) # data - массив размерностью 1 строчка и 25 столбцов

import pickle
import numpy as np
from sklearn.preprocessing import StandardScaler
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score
from sklearn import svm
from libsvm.svmutil import *
 
vectors_0 = np.loadtxt('../vector_0.txt')
vectors_1 = np.loadtxt('../vector_1.txt')
 
label_names = list()
labels = list()
for i in range(24):
    label_names.append('0')
    labels.append(0)
for i in range(18):
    label_names.append('1')
    labels.append(1)
 
feature_names = ['Vector activity']
features = np.vstack([vectors_0, vectors_1])
 
scaler = StandardScaler().fit_transform(features)
train, test, train_labels, test_labels = train_test_split(scaler, labels, test_size=0.3, random_state=100)
 
svm = svm.SVC(kernel='rbf', gamma=1, C=1, cache_size=1024, max_iter=1000000)
model_svm = svm.fit(train, train_labels)
preds_svm = svm.predict(test)
acc_svm = accuracy_score(test_labels, preds_svm)
 
print(f'SVM accuracy is: {acc_svm * 100}')
 
with open('../../models/svm_model.pkl', 'wb') as f:
    pickle.dump(model_svm, f)

def predictions():
    vector_new = np.loadtxt('calculations/vector_new.txt', float)
 
    with open("models/svm_model.pkl", "rb") as f:
        model = pickle.load(f)
 
    vectors_0 = np.loadtxt('../vector_0.txt')
    vectors_1 = np.loadtxt('../vector_1.txt')
 
    features = np.vstack([vectors_0, vectors_1])
    scaler = StandardScaler().fit(features)
    features = scaler.transform(vector_new)
 
    for el in features:
        preds = model.predict(el)
        print(preds[0])