将数据映射到正态分布 | 您所在的位置:网站首页 › QuantileTransformer方法 › 将数据映射到正态分布 |
# 作者: Eric Chang # Nicolas Hug # 执照: BSD 3 clause import numpy as npimport matplotlib.pyplot as plt from sklearn.preprocessing import PowerTransformerfrom sklearn.preprocessing import QuantileTransformerfrom sklearn.model_selection import train_test_split print(__doc__) N_SAMPLES = 1000FONT_SIZE = 6BINS = 30 rng = np.random.RandomState(304)bc = PowerTransformer(method='box-cox')yj = PowerTransformer(method='yeo-johnson')# n_quantiles设置为训练集大小,而不是默认值,以避免此示例引发警告qt = QuantileTransformer(n_quantiles=500, output_distribution='normal', random_state=rng)size = (N_SAMPLES, 1) # 对数正态分布X_lognormal = rng.lognormal(size=size) # 卡方分布df = 3X_chisq = rng.chisquare(df=df, size=size) # 威布尔分布a = 50X_weibull = rng.weibull(a=a, size=size) # 高斯分布loc = 100X_gaussian = rng.normal(loc=loc, size=size) # 均匀分布X_uniform = rng.uniform(low=0, high=1, size=size) # 双峰分布loc_a, loc_b = 100, 105X_a, X_b = rng.normal(loc=loc_a, size=size), rng.normal(loc=loc_b, size=size)X_bimodal = np.concatenate([X_a, X_b], axis=0) # 绘制图像distributions = [ ('Lognormal', X_lognormal), ('Chi-squared', X_chisq), ('Weibull', X_weibull), ('Gaussian', X_gaussian), ('Uniform', X_uniform), ('Bimodal', X_bimodal)] colors = ['#D81B60', '#0188FF', '#FFC107', '#B7A2FF', '#000000', '#2EC5AC'] fig, axes = plt.subplots(nrows=8, ncols=3, figsize=plt.figaspect(2))axes = axes.flatten()axes_idxs = [(0, 3, 6, 9), (1, 4, 7, 10), (2, 5, 8, 11), (12, 15, 18, 21), (13, 16, 19, 22), (14, 17, 20, 23)]axes_list = [(axes[i], axes[j], axes[k], axes[l]) for (i, j, k, l) in axes_idxs] for distribution, color, axes in zip(distributions, colors, axes_list): name, X = distribution X_train, X_test = train_test_split(X, test_size=.5) # 执行幂变换和分位数变换 X_trans_bc = bc.fit(X_train).transform(X_test) lmbda_bc = round(bc.lambdas_[0], 2) X_trans_yj = yj.fit(X_train).transform(X_test) lmbda_yj = round(yj.lambdas_[0], 2) X_trans_qt = qt.fit(X_train).transform(X_test) ax_original, ax_bc, ax_yj, ax_qt = axes ax_original.hist(X_train, color=color, bins=BINS) ax_original.set_title(name, fontsize=FONT_SIZE) ax_original.tick_params(axis='both', which='major', labelsize=FONT_SIZE) for ax, X_trans, meth_name, lmbda in zip( (ax_bc, ax_yj, ax_qt), (X_trans_bc, X_trans_yj, X_trans_qt), ('Box-Cox', 'Yeo-Johnson', 'Quantile transform'), (lmbda_bc, lmbda_yj, None)): ax.hist(X_trans, color=color, bins=BINS) title = 'After {}'.format(meth_name) if lmbda is not None: title += r'\n$\lambda$ = {}'.format(lmbda) ax.set_title(title, fontsize=FONT_SIZE) ax.tick_params(axis='both', which='major', labelsize=FONT_SIZE) ax.set_xlim([-3.5, 3.5]) plt.tight_layout()plt.show() |
CopyRight 2018-2019 实验室设备网 版权所有 |