利用Sklearn中的逻辑回归（LogisticRegression）对手写数字（load_digits） - ToB企服应用市场:ToB评测及商务社交产业平台

from sklearn.datasets import load_digits

复制代码

"""Load and return the digits dataset (classification).
Each datapoint is a 8x8 image of a digit.
================= ==============
Classes 10
Samples per class ~180
Samples total 1797
Dimensionality 64
Features integers 0-16
================= ==============
This is a copy of the test set of the UCI ML hand-written digits datasets
https://archive.ics.uci.edu/ml/datasets/Optical+Recognition+of+Handwritten+Digits
Read more in the :ref:`User Guide <digits_dataset>`.
Parameters
----------
n_class : int, default=10
The number of classes to return. Between 0 and 10.
return_X_y : bool, default=False
If True, returns ``(data, target)`` instead of a Bunch object.
See below for more information about the `data` and `target` object.
.. versionadded:: 0.18
as_frame : bool, default=False
If True, the data is a pandas DataFrame including columns with
appropriate dtypes (numeric). The target is
a pandas DataFrame or Series depending on the number of target columns.
If `return_X_y` is True, then (`data`, `target`) will be pandas
DataFrames or Series as described below.
.. versionadded:: 0.23
Returns
-------
data : :class:`~sklearn.utils.Bunch`
Dictionary-like object, with the following attributes.
data : {ndarray, dataframe} of shape (1797, 64)
The flattened data matrix. If `as_frame=True`, `data` will be
a pandas DataFrame.
target: {ndarray, Series} of shape (1797,)
The classification target. If `as_frame=True`, `target` will be
a pandas Series.
feature_names: list
The names of the dataset columns.
target_names: list
The names of target classes.
.. versionadded:: 0.20
frame: DataFrame of shape (1797, 65)
Only present when `as_frame=True`. DataFrame with `data` and
`target`.
.. versionadded:: 0.23
images: {ndarray} of shape (1797, 8, 8)
The raw image data.
DESCR: str
The full description of the dataset.
(data, target) : tuple if ``return_X_y`` is True
A tuple of two ndarrays by default. The first contains a 2D ndarray of
shape (1797, 64) with each row representing one sample and each column
representing the features. The second ndarray of shape (1797) contains
the target samples. If `as_frame=True`, both arrays are pandas objects,
i.e. `X` a dataframe and `y` a series.
.. versionadded:: 0.18
Examples
--------
To load the data and visualize the images::
>>> from sklearn.datasets import load_digits
>>> digits = load_digits()
>>> print(digits.data.shape)
(1797, 64)
>>> import matplotlib.pyplot as plt
>>> plt.gray()
>>> plt.matshow(digits.images[0])
<...>
>>> plt.show()
"""

复制代码

# 获取数据集数据和标签
datas = load_digits()
X_data = datas.data
y_data = datas.target

复制代码

from matplotlib import pyplot as plt
# 展示前十个数据的图像
fig, ax = plt.subplots(
nrows=2,
ncols=5,
sharex=True,
sharey=True, )
ax = ax.flatten()
for i in range(10):
ax[i].imshow(datas.data[i].reshape((8, 8)), cmap='Greys', interpolation='nearest')
plt.show()

复制代码

# 划分数据集
X_train, X_test, y_train, y_test = train_test_split(X_data, y_data, test_size=0.3)

复制代码

# 建立逻辑回归模型
model = LogisticRegression(max_iter=10000, random_state=42, multi_class='multinomial')
# 训练模型
model.fit(X_train, y_train)

复制代码

scores = cross_val_score(model, X_train, y_train, cv=10) # 十折交叉验证
k = 0
for i in scores:
k += i
print("十折交叉验证平均值：", k / 10)
print(f"十折交叉验证:{scores}\n")

复制代码

y_pred = model.predict(X_test)
error_rate = model.score(X_test, y_test)
print(f"错误率:{error_rate}\n")
print(f"测试集预测值:{y_pred}\n")

复制代码

from sklearn.linear_model import LogisticRegressionfrom sklearn.datasets import load_digitsfrom sklearn.model_selection import cross_val_score, train_test_splitfrom matplotlib import pyplot as plt# 获取数据集数据和标签
datas = load_digits()
X_data = datas.data
y_data = datas.target# 展示前十个数据的图像fig, ax = plt.subplots( nrows=2, ncols=5, sharex=True, sharey=True, )ax = ax.flatten()for i in range(10): ax[i].imshow(datas.data[i].reshape((8, 8)), cmap='Greys', interpolation='nearest')plt.show()# 划分数据集
X_train, X_test, y_train, y_test = train_test_split(X_data, y_data, test_size=0.3)# 建立逻辑回归模子model = LogisticRegression(max_iter=10000, random_state=42, multi_class='multinomial')scores = cross_val_score(model, X_train, y_train, cv=10) # 十折交叉验证k = 0for i in scores: k += iprint("十折交叉验证平均值：", k / 10)model.fit(X_train, y_train)y_pred = model.predict(X_test)error_rate = model.score(X_test, y_test)print(f"十折交叉验证:{scores}\n")print(f"错误率:{error_rate}\n")print(f"测试集猜测值:{y_pred}\n")

复制代码