sklearn可視化不同資料劃分方法的差異：TimeSeriesSplit, KFold, ShuffleSplit,StratifiedKFold, GroupShuffleSplit,GroupKFold, StratifiedShuffleSplit

#包匯入

#仿真資料集

#定義查看不同交叉驗證資料劃分形式的函式

#KFold交叉驗證資料劃分

#StratifiedKFold交叉驗證資料劃分

#同時查看KFold, GroupKFold, ShuffleSplit, StratifiedKFold,GroupShuffleSplit, StratifiedShuffleSplit, TimeSeriesSplit交叉驗證資料劃分

選擇合適的交叉驗證物件是正確擬合模型的關鍵部分，為了避免模型過擬合、規范測驗集中的組數等，有許多方法可以將資料拆分為訓練集和測驗集，

#包匯入

from sklearn.model_selection import (TimeSeriesSplit, KFold, ShuffleSplit,
                                     StratifiedKFold, GroupShuffleSplit,
                                     GroupKFold, StratifiedShuffleSplit)
import numpy as np
import matplotlib.pyplot as plt
from matplotlib.patches import Patch
np.random.seed(1338)
cmap_data = plt.cm.Paired
cmap_cv = plt.cm.coolwarm
n_splits = 4

首先，我們必須了解我們資料的結構，它有100個隨機生成的輸入資料樣本，3個類在樣本上不均勻地分布，資料中的10個組在資料上均勻地分布，

正如我們將看到的，一些交叉驗證物件對標記的資料執行特定的操作，其他的對分組的資料執行不同的操作，而其他的則不使用這些分組資訊，

#仿真資料集

# Generate the class/group data
n_points = 100
X = np.random.randn(100, 10)

percentiles_classes = [.1, .3, .6]
y = np.hstack([[ii] * int(100 * perc)
               for ii, perc in enumerate(percentiles_classes)])

# Evenly spaced groups repeated once
groups = np.hstack([[ii] * 10 for ii in range(10)])


def visualize_groups(classes, groups, name):
    # Visualize dataset groups
    fig, ax = plt.subplots()
    ax.scatter(range(len(groups)),  [.5] * len(groups), c=groups, marker='_',
               lw=50, cmap=cmap_data)
    ax.scatter(range(len(groups)),  [3.5] * len(groups), c=classes, marker='_',
               lw=50, cmap=cmap_data)
    ax.set(ylim=[-1, 5], yticks=[.5, 3.5],
           yticklabels=['Data\ngroup', 'Data\nclass'], xlabel="Sample index")


visualize_groups(y, groups, 'no groups')

plot cv indices

#定義查看不同交叉驗證資料劃分形式的函式

def plot_cv_indices(cv, X, y, group, ax, n_splits, lw=10):
    """Create a sample plot for indices of a cross-validation object."""

    # Generate the training/testing visualizations for each CV split
    for ii, (tr, tt) in enumerate(cv.split(X=X, y=y, groups=group)):
        # Fill in indices with the training/test groups
        indices = np.array([np.nan] * len(X))
        indices[tt] = 1
        indices[tr] = 0

        # Visualize the results
        ax.scatter(range(len(indices)), [ii + .5] * len(indices),
                   c=indices, marker='_', lw=lw, cmap=cmap_cv,
                   vmin=-.2, vmax=1.2)

    # Plot the data classes and groups at the end
    ax.scatter(range(len(X)), [ii + 1.5] * len(X),
               c=y, marker='_', lw=lw, cmap=cmap_data)

    ax.scatter(range(len(X)), [ii + 2.5] * len(X),
               c=group, marker='_', lw=lw, cmap=cmap_data)

    # Formatting
    yticklabels = list(range(n_splits)) + ['class', 'group']
    ax.set(yticks=np.arange(n_splits+2) + .5, yticklabels=yticklabels,
           xlabel='Sample index', ylabel="CV iteration",
           ylim=[n_splits+2.2, -.2], xlim=[0, 100])
    ax.set_title('{}'.format(type(cv).__name__), fontsize=15)
    return ax

#KFold交叉驗證資料劃分

fig, ax = plt.subplots()
cv = KFold(n_splits)
plot_cv_indices(cv, X, y, groups, ax, n_splits)

KFold

#StratifiedKFold交叉驗證資料劃分

fig, ax = plt.subplots()
cv = StratifiedKFold(n_splits)
plot_cv_indices(cv, X, y, groups, ax, n_splits)

StratifiedKFold

#同時查看KFold, GroupKFold, ShuffleSplit, StratifiedKFold,GroupShuffleSplit, StratifiedShuffleSplit, TimeSeriesSplit交叉驗證資料劃分

cvs = [KFold, GroupKFold, ShuffleSplit, StratifiedKFold,
       GroupShuffleSplit, StratifiedShuffleSplit, TimeSeriesSplit]


for cv in cvs:
    this_cv = cv(n_splits=n_splits)
    fig, ax = plt.subplots(figsize=(6, 3))
    plot_cv_indices(this_cv, X, y, groups, ax, n_splits)

    ax.legend([Patch(color=cmap_cv(.8)), Patch(color=cmap_cv(.02))],
              ['Testing set', 'Training set'], loc=(1.02, .8))
    # Make the legend fit
    plt.tight_layout()
    fig.subplots_adjust(right=.7)
plt.show()

KFold