class DataEncoder(object): # 支持三种编码方式
def __init__(self, encoder_type):
assert encoder_type in {"one_hot", "label", "Ordinal"}
self.encoder_type = encoder_type
if self.encoder_type == "one_hot": # 种类的编码
self.encodermodule = OneHotEncoder(categories='auto', drop=None, sparse=True,
dtype=np.float64, handle_unknown='error')
# categories 可取 "auto" 或种类的列表
# drop 可取 {‘first’, ‘if_binary’} None 或 array [i] 表示丢弃第i个
# first 表示丢弃每个种类特征的第一个， 二进制
# sparse 返回一个稀疏矩阵，否则返回一个数组
# handle_unknown {‘error’, ‘ignore’}, default=’error’
elif self.encoder_type == "label":
self.encodermodule = LabelEncoder()
elif self.encoder_type == "Ordinal": # 序号编码
self.encodermodule = OrdinalEncoder(categories="auto", dtype=np.float64)
# categories 用法与onehot 差不多
else:
raise ValueError("please select a correct encoder_type")
def fit_transform(self, data):
return self.encodermodule.fit_transform(data)
def fit(self, data):
self.encodermodule.fit(data)
def transform(self, data):
self.encodermodule.transform(data)
def set_params(self, params):
self.encodermodule.set_params(**params)
def get_params(self):
return self.encodermodule.get_params(deep=True)
def inverse_transform(self, data):
return self.encodermodule.inverse_transform(data)
def get_classes(self):
assert self.encoder_type in {"label"}
return self.encodermodule.classes_
def get_category(self):
assert self.encoder_type in {"one_hot", "Ordinal"}
return self.encodermodule.categories_ # 返回数组列表
def get_feature_names(self, output_feature): # 获取输出特征的特征名字
assert self.encoder_type in {"one_hot"}
return self.encodermodule.get_feature_names(output_feature)
class SibSpBinner(BaseEstimator, TransformerMixin):
def __init__(self, thresh=2, encode='ord', sparse=False):
if thresh > 7:
raise ValueError('Specify a value less than 7')
self.thresh = thresh
self.cat = self.get_cat(thresh)
self.encode = encode
self.sparse = sparse
if encode == 'ohe':
self.enc = OneHotEncoder([self.cat],
drop=[self.cat[-1]],
sparse=sparse)
elif encode == 'ord':
self.enc = OrdinalEncoder([self.cat])
def fit(self, X, y=None):
if self.encode in ['ohe', 'ord']:
try:
self.name = X.name
except AttributeError:
self.name = 'SibSp'
dummy_df = pd.DataFrame({self.name: ['0']})
self.enc.fit(dummy_df)
return self
@staticmethod
def get_cat(thresh):
return [str(x) for x in range(thresh + 1)] + [f'>{thresh}']
def transform(self, X):
X = X.copy()
X[X > self.thresh] = f'>{self.thresh}'
X = pd.DataFrame(X).astype(str)
if self.encode in ['ohe', 'ord']:
X = self.enc.transform(X)
return X
def get_feature_names(self, input_features=None):
if self.encode in ['ohe', 'ord']:
return self.enc.get_feature_names(input_features)
# ```
# %%
from sklearn.preprocessing import OneHotEncoder
encoder = OneHotEncoder(sparse=False)
education_encoded = encoder.fit_transform(education_column)
education_encoded
# %% [markdown]
# We see that encoding a single feature will give a NumPy array full of zeros
# and ones. We can get a better understanding using the associated feature
# names resulting from the transformation.
# %%
feature_names = encoder.get_feature_names(input_features=["education"])
education_encoded = pd.DataFrame(education_encoded, columns=feature_names)
education_encoded
# %% [markdown]
# As we can see, each category (unique value) became a column; the encoding
# returned, for each sample, a 1 to specify which category it belongs to.
#
# Let's apply this encoding on the full dataset.
# %%
print(f"The dataset is composed of {data_categorical.shape[1]} features")
data_categorical.head()
# %%
data_encoded = encoder.fit_transform(data_categorical)
# In[]: from sklearn.preprocessing import OneHotEncoder X = data_.iloc[:,1:-1] enc = OneHotEncoder(categories='auto').fit(X) result = enc.transform(X).toarray() #依然可以直接一步到位，但为了给大家展示模型属性，所以还是写成了三步 OneHotEncoder(categories='auto').fit_transform(X).toarray() #依然可以还原 pd.DataFrame(enc.inverse_transform(result)) print(enc.get_feature_names()) # 返回每一个经过哑变量后生成稀疏矩阵列的名字 # axis=1,表将两表左右相连，如果是axis=0，就是将量表上下相连 newdata = pd.concat([data,pd.DataFrame(result)],axis=1) newdata.drop(["Sex","Embarked"],axis=1,inplace=True) newdata.columns = ["Age","Survived","Female","Male","Embarked_C","Embarked_Q","Embarked_S"] # In[]: # 5、连续变量转换： # 将年龄二值化 data_2 = data.copy() from sklearn.preprocessing import Binarizer X = data_2.iloc[:,0].values.reshape(-1,1) #类为特征专用，所以不能使用一维数组
print(f"The dataset is composed of {data_categorical.shape[1]} features")
data_categorical.head()
# %%
from sklearn.preprocessing import OneHotEncoder
encoder = OneHotEncoder(sparse=False)
data_encoded = encoder.fit_transform(data_categorical)
print(f"The dataset encoded contains {data_encoded.shape[1]} features")
data_encoded
# %% [markdown]
# Let's wrap this numpy array in a dataframe with informative column names as provided by the encoder object:
# %%
columns_encoded = encoder.get_feature_names(data_categorical.columns)
pd.DataFrame(data_encoded, columns=columns_encoded).head()
# %% [markdown]
# Look at how the workclass variable of the first 3 records has been encoded and compare this to the original string representation.
#
# The number of features after the encoding is than 10 times larger than in the
# original data because some variables such as `occupation` and `native-country`
# have many possible categories.
#
# We can now integrate this encoder inside a machine learning pipeline as in the
# case with numerical data: let's train a linear classifier on
# the encoded data and check the performance of this machine learning pipeline
# using cross-validation.
# %%
# avoid obtaining a sparse matrix, which is less efficient but easier to
# inspect results for didactic purposes.
# ```
# %%
from sklearn.preprocessing import OneHotEncoder
encoder = OneHotEncoder(sparse=False)
education_encoded = encoder.fit_transform(education_column)
# %% [markdown]
# As in the previous section, we will visually check the encoding.
# %%
df = pd.DataFrame(education_encoded[:10],
columns=encoder.get_feature_names(education_column.columns))
ax = sns.heatmap(df, annot=True, cmap="RdBu", cbar=False)
ax.set_ylabel("Sample index")
_ = ax.set_title("Ordinal encoding of 'education' column")
# %% [markdown]
# So we observed that each category in education becomes a column and the
# data resulting from the encoding is indicating whether or not the sample
# belong to this category.
#
# Let's apply this encoding on the full dataset.
# %%
print(f"The dataset is composed of {data_categorical.shape[1]} features")
data_categorical.head()
