# http://www.scikit-yb.org/zh/latest/tutorial.html

选择和/或设计最小和最具预测性的特性集
从模型家族中选择一组算法，并且
优化算法超参数以优化性能。

import os
import pandas as pd
mushrooms = 'data/shrooms.csv'  # 数据集
dataset   = pd.read_csv(mushrooms)
# dataset.columns = names
dataset.head()

features = ['cap-shape', 'cap-surface', 'cap-color']
target   = ['class']
X = dataset[features]
y = dataset[target]
dataset.shape # 较官方文档少了俩蘑菇
(8122, 25)
dataset.groupby('class').count() # 各少了1个蘑菇

from sklearn.base import BaseEstimator, TransformerMixin
from sklearn.preprocessing import LabelEncoder, OneHotEncoder
class EncodeCategorical(BaseEstimator, TransformerMixin):
    """
    Encodes a specified list of columns or all columns if None.
    """

    def __init__(self, columns=None):
        self.columns  = [col for col in columns]
        self.encoders = None

    def fit(self, data, target=None):
        """
        Expects a data frame with named columns to encode.
        """
        # Encode all columns if columns is None
        if self.columns is None:
            self.columns = data.columns

        # Fit a label encoder for each column in the data frame
        self.encoders = {
            column: LabelEncoder().fit(data[column])
            for column in self.columns
        }
        return self

    def transform(self, data):
        """
        Uses the encoders to transform a data frame.
        """
        output = data.copy()
        for column, encoder in self.encoders.items():
            output[column] = encoder.transform(data[column])

        return output

from sklearn.metrics import f1_score
from sklearn.pipeline import Pipeline
def model_selection(X, y, estimator):
    """
    Test various estimators.
    """
    y = LabelEncoder().fit_transform(y.values.ravel())
    model = Pipeline([
         ('label_encoding', EncodeCategorical(X.keys())),
         ('one_hot_encoder', OneHotEncoder(categories='auto')),  # 此处增加自动分类，否则有warning
         ('estimator', estimator)
    ])

    # Instantiate the classification model and visualizer
    model.fit(X, y)

    expected  = y
    predicted = model.predict(X)

    # Compute and return the F1 score (the harmonic mean of precision and recall)
    return (f1_score(expected, predicted))
from sklearn.svm import LinearSVC, NuSVC, SVC
from sklearn.neighbors import KNeighborsClassifier
from sklearn.linear_model import LogisticRegressionCV, LogisticRegression, SGDClassifier
from sklearn.ensemble import BaggingClassifier, ExtraTreesClassifier, RandomForestClassifier
model_selection(X, y, LinearSVC())
0.6582119537920643
import warnings
warnings.filterwarnings("ignore", category=FutureWarning, module="sklearn")  # 忽略警告
model_selection(X, y, NuSVC())
0.6878837238441299
model_selection(X, y, SVC())
0.6625145971195017
model_selection(X, y, SGDClassifier())
0.5738408700629649
model_selection(X, y, KNeighborsClassifier())
0.6856846473029046
model_selection(X, y, LogisticRegressionCV())
0.6582119537920643
model_selection(X, y, LogisticRegression())
0.6578749058025622
model_selection(X, y, BaggingClassifier())
0.6873901878632248
model_selection(X, y, ExtraTreesClassifier())
0.6872294372294372
model_selection(X, y, RandomForestClassifier())
0.6992081007399714

from sklearn.pipeline import Pipeline
from yellowbrick.classifier import ClassificationReport


def visual_model_selection(X, y, estimator):
    """
    Test various estimators.
    """
    y = LabelEncoder().fit_transform(y.values.ravel())
    model = Pipeline([
         ('label_encoding', EncodeCategorical(X.keys())),
         ('one_hot_encoder', OneHotEncoder()),
         ('estimator', estimator)
    ])

    # Instantiate the classification model and visualizer
    visualizer = ClassificationReport(model, classes=['edible', 'poisonous'])
    visualizer.fit(X, y)
    visualizer.score(X, y)
    visualizer.poof()
visual_model_selection(X, y, LinearSVC())

# 其他分类器可视化略
visual_model_selection(X, y, RandomForestClassifier())

现在,哪种模型看起来最好?为什么?
哪一个模型最有可能救你的命?
可视化模型评估与数值模型评价，体验起来有何不同?