# Load data set df = pd.read_csv("./HTRU_2.csv", hearer=None) X = df.iloc[:, :-1] y = df.iloc[:, -1:].values # Normalization normalizer = StandardScaler() X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, stratify=y, random_state=42) X_train = normalizer.fit_transform(X_train) X_test = normalizer.transform(X_test) X_train, y_train = preprocess.upsampling(X_train, y_train, ratio=1 / 5) # Train model with fine-tuned parameters lr = LogisticRegression(solver='liblinear', penalty='l1', tol=0.0001, C=0.1, n_jobs=-1, random_state=95) clf_lr = lr.fit(X_train, y_train) # Cross validation cv = ShuffleSplit(n_splits=5, test_size=0.3, random_state=95) res = {} for scoring in ('f1', 'roc_auc', 'precision', 'recall'): res[scoring] = cross_val_score(clf_lr,
# coding=utf-8 # Author = 'QQ' import numpy as np import matplotlib.pyplot as plt import pandas as pd import preprocess audio_path = '3.mp3' action_path = '3.csv' mfcc = preprocess.mff_extract(audio_path) actions = preprocess.upsampling(action_path) action_frame = preprocess.actions_frame(actions) action_filled = np.pad(action_frame, ((0, mfcc.shape[0] - action_frame.shape[0]), (0, 0)), 'edge') sample = np.hstack([mfcc, action_filled]) np.savetxt('3.txt', sample) sample = np.loadtxt('3.txt') # 以上为数据预处理代码 actions.to_csv('actions.csv') action_frame = pd.DataFrame(action_frame.T) action_frame.to_csv('action_frame.csv') # stft detail # By default, use the entire frame win_length = n_fft window = 'hann' dtype = np.complex64