建模与评估
1、载入建模数据
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns #一个作图工具
from IPython.display import Image
%matplotlib inline
#将那些用matplotlib绘制的图显示在页面里而不是弹出一个窗口。
#matplotlib是Python的2D绘图库。
#Matplotlib可以自行画任意图;seaborn是套餐类型,已经制作好的现成的。
plt.rcParams['font.sans-serif'] = ['SimHei'] # 用来正常显示中文标签
plt.rcParams['axes.unicode_minus'] = False # 用来正常显示负号
plt.rcParams['figure.figsize'] = (10, 6) # 设置输出图片大小
plt.rcParams.keys()
#调用plt.rcParams的全部参数
#'figure.dpi': 100.0 每英寸点数
#'figure.figsize': [6.0, 4.0] 生成的图表最大尺寸
#'font.size': 10.0 字体大小
#'hist.bins': 10 直方图分箱个数
#'lines.linewidth': 1.5 线宽
#'lines.marker': 'None' 标记样式
#'savefig.format': 'png' 保存图片的格式
#'savefig.jpeg_quality': 95 图片质量
#'text.color': 'black' 文本颜色
#'timezone': 'UTC' 时区格式
KeysView(RcParams({'_internal.classic_mode': False,
'agg.path.chunksize': 0,
'animation.avconv_args': [],
'animation.avconv_path': 'avconv',
'animation.bitrate': -1,
'animation.codec': 'h264',
'animation.convert_args': [],
'animation.convert_path': 'convert',
'animation.embed_limit': 20.0,
'animation.ffmpeg_args': [],
'animation.ffmpeg_path': 'ffmpeg',
'animation.frame_format': 'png',
'animation.html': 'none',
'animation.html_args': [],
'animation.writer': 'ffmpeg',
'axes.autolimit_mode': 'data',
'axes.axisbelow': 'line',
'axes.edgecolor': 'black',
'axes.facecolor': 'white',
'axes.formatter.limits': [-5, 6],
'axes.formatter.min_exponent': 0,
'axes.formatter.offset_threshold': 4,
'axes.formatter.use_locale': False,
'axes.formatter.use_mathtext': False,
'axes.formatter.useoffset': True,
'axes.grid': False,
'axes.grid.axis': 'both',
'axes.grid.which': 'major',
'axes.labelcolor': 'black',
'axes.labelpad': 4.0,
'axes.labelsize': 'medium',
'axes.labelweight': 'normal',
'axes.linewidth': 0.8,
'axes.prop_cycle': cycler('color', ['#1f77b4', '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2', '#7f7f7f', '#bcbd22', '#17becf']),
'axes.spines.bottom': True,
'axes.spines.left': True,
'axes.spines.right': True,
'axes.spines.top': True,
'axes.titlecolor': 'auto',
'axes.titlelocation': 'center',
'axes.titlepad': 6.0,
'axes.titlesize': 'large',
'axes.titleweight': 'normal',
'axes.unicode_minus': False,
'axes.xmargin': 0.05,
'axes.ymargin': 0.05,
'axes3d.grid': True,
'backend': 'module://ipykernel.pylab.backend_inline',
'backend_fallback': True,
'boxplot.bootstrap': None,
'boxplot.boxprops.color': 'black',
'boxplot.boxprops.linestyle': '-',
'boxplot.boxprops.linewidth': 1.0,
'boxplot.capprops.color': 'black',
'boxplot.capprops.linestyle': '-',
'boxplot.capprops.linewidth': 1.0,
'boxplot.flierprops.color': 'black',
'boxplot.flierprops.linestyle': 'none',
'boxplot.flierprops.linewidth': 1.0,
'boxplot.flierprops.marker': 'o',
'boxplot.flierprops.markeredgecolor': 'black',
'boxplot.flierprops.markeredgewidth': 1.0,
'boxplot.flierprops.markerfacecolor': 'none',
'boxplot.flierprops.markersize': 6.0,
'boxplot.meanline': False,
'boxplot.meanprops.color': 'C2',
'boxplot.meanprops.linestyle': '--',
'boxplot.meanprops.linewidth': 1.0,
'boxplot.meanprops.marker': '^',
'boxplot.meanprops.markeredgecolor': 'C2',
'boxplot.meanprops.markerfacecolor': 'C2',
'boxplot.meanprops.markersize': 6.0,
'boxplot.medianprops.color': 'C1',
'boxplot.medianprops.linestyle': '-',
'boxplot.medianprops.linewidth': 1.0,
'boxplot.notch': False,
'boxplot.patchartist': False,
'boxplot.showbox': True,
'boxplot.showcaps': True,
'boxplot.showfliers': True,
'boxplot.showmeans': False,
'boxplot.vertical': True,
'boxplot.whiskerprops.color': 'black',
'boxplot.whiskerprops.linestyle': '-',
'boxplot.whiskerprops.linewidth': 1.0,
'boxplot.whiskers': 1.5,
'contour.corner_mask': True,
'contour.negative_linestyle': 'dashed',
'datapath': 'D:\\anaconda\\lib\\site-packages\\matplotlib\\mpl-data',
'date.autoformatter.day': '%Y-%m-%d',
'date.autoformatter.hour': '%m-%d %H',
'date.autoformatter.microsecond': '%M:%S.%f',
'date.autoformatter.minute': '%d %H:%M',
'date.autoformatter.month': '%Y-%m',
'date.autoformatter.second': '%H:%M:%S',
'date.autoformatter.year': '%Y',
'docstring.hardcopy': False,
'errorbar.capsize': 0.0,
'figure.autolayout': False,
'figure.constrained_layout.h_pad': 0.04167,
'figure.constrained_layout.hspace': 0.02,
'figure.constrained_layout.use': False,
'figure.constrained_layout.w_pad': 0.04167,
'figure.constrained_layout.wspace': 0.02,
'figure.dpi': 72.0,
'figure.edgecolor': (1, 1, 1, 0),
'figure.facecolor': (1, 1, 1, 0),
'figure.figsize': [10.0, 6.0],
'figure.frameon': True,
'figure.max_open_warning': 20,
'figure.subplot.bottom': 0.125,
'figure.subplot.hspace': 0.2,
'figure.subplot.left': 0.125,
'figure.subplot.right': 0.9,
'figure.subplot.top': 0.88,
'figure.subplot.wspace': 0.2,
'figure.titlesize': 'large',
'figure.titleweight': 'normal',
'font.cursive': ['Apple Chancery',
'Textile',
'Zapf Chancery',
'Sand',
'Script MT',
'Felipa',
'cursive'],
'font.family': ['sans-serif'],
'font.fantasy': ['Comic Neue',
'Comic Sans MS',
'Chicago',
'Charcoal',
'Impact',
'Western',
'Humor Sans',
'xkcd',
'fantasy'],
'font.monospace': ['DejaVu Sans Mono',
'Bitstream Vera Sans Mono',
'Computer Modern Typewriter',
'Andale Mono',
'Nimbus Mono L',
'Courier New',
'Courier',
'Fixed',
'Terminal',
'monospace'],
'font.sans-serif': ['SimHei'],
'font.serif': ['DejaVu Serif',
'Bitstream Vera Serif',
'Computer Modern Roman',
'New Century Schoolbook',
'Century Schoolbook L',
'Utopia',
'ITC Bookman',
'Bookman',
'Nimbus Roman No9 L',
'Times New Roman',
'Times',
'Palatino',
'Charter',
'serif'],
'font.size': 10.0,
'font.stretch': 'normal',
'font.style': 'normal',
'font.variant': 'normal',
'font.weight': 'normal',
'grid.alpha': 1.0,
'grid.color': '#b0b0b0',
'grid.linestyle': '-',
'grid.linewidth': 0.8,
'hatch.color': 'black',
'hatch.linewidth': 1.0,
'hist.bins': 10,
'image.aspect': 'equal',
'image.cmap': 'viridis',
'image.composite_image': True,
'image.interpolation': 'antialiased',
'image.lut': 256,
'image.origin': 'upper',
'image.resample': True,
'interactive': True,
'keymap.all_axes': ['a'],
'keymap.back': ['left', 'c', 'backspace', 'MouseButton.BACK'],
'keymap.copy': ['ctrl+c', 'cmd+c'],
'keymap.forward': ['right', 'v', 'MouseButton.FORWARD'],
'keymap.fullscreen': ['f', 'ctrl+f'],
'keymap.grid': ['g'],
'keymap.grid_minor': ['G'],
'keymap.help': ['f1'],
'keymap.home': ['h', 'r', 'home'],
'keymap.pan': ['p'],
'keymap.quit': ['ctrl+w', 'cmd+w', 'q'],
'keymap.quit_all': ['W', 'cmd+W', 'Q'],
'keymap.save': ['s', 'ctrl+s'],
'keymap.xscale': ['k', 'L'],
'keymap.yscale': ['l'],
'keymap.zoom': ['o'],
'legend.borderaxespad': 0.5,
'legend.borderpad': 0.4,
'legend.columnspacing': 2.0,
'legend.edgecolor': '0.8',
'legend.facecolor': 'inherit',
'legend.fancybox': True,
'legend.fontsize': 'medium',
'legend.framealpha': 0.8,
'legend.frameon': True,
'legend.handleheight': 0.7,
'legend.handlelength': 2.0,
'legend.handletextpad': 0.8,
'legend.labelspacing': 0.5,
'legend.loc': 'best',
'legend.markerscale': 1.0,
'legend.numpoints': 1,
'legend.scatterpoints': 1,
'legend.shadow': False,
'legend.title_fontsize': None,
'lines.antialiased': True,
'lines.color': 'C0',
'lines.dash_capstyle': 'butt',
'lines.dash_joinstyle': 'round',
'lines.dashdot_pattern': [6.4, 1.6, 1.0, 1.6],
'lines.dashed_pattern': [3.7, 1.6],
'lines.dotted_pattern': [1.0, 1.65],
'lines.linestyle': '-',
'lines.linewidth': 1.5,
'lines.marker': 'None',
'lines.markeredgecolor': 'auto',
'lines.markeredgewidth': 1.0,
'lines.markerfacecolor': 'auto',
'lines.markersize': 6.0,
'lines.scale_dashes': True,
'lines.solid_capstyle': 'projecting',
'lines.solid_joinstyle': 'round',
'markers.fillstyle': 'full',
'mathtext.bf': 'sans:bold',
'mathtext.cal': 'cursive',
'mathtext.default': 'it',
'mathtext.fallback_to_cm': True,
'mathtext.fontset': 'dejavusans',
'mathtext.it': 'sans:italic',
'mathtext.rm': 'sans',
'mathtext.sf': 'sans',
'mathtext.tt': 'monospace',
'mpl_toolkits.legacy_colorbar': True,
'patch.antialiased': True,
'patch.edgecolor': 'black',
'patch.facecolor': 'C0',
'patch.force_edgecolor': False,
'patch.linewidth': 1.0,
'path.effects': [],
'path.simplify': True,
'path.simplify_threshold': 0.1111111111111111,
'path.sketch': None,
'path.snap': True,
'pdf.compression': 6,
'pdf.fonttype': 3,
'pdf.inheritcolor': False,
'pdf.use14corefonts': False,
'pgf.preamble': '',
'pgf.rcfonts': True,
'pgf.texsystem': 'xelatex',
'polaraxes.grid': True,
'ps.distiller.res': 6000,
'ps.fonttype': 3,
'ps.papersize': 'letter',
'ps.useafm': False,
'ps.usedistiller': None,
'savefig.bbox': None,
'savefig.directory': '~',
'savefig.dpi': 'figure',
'savefig.edgecolor': 'white',
'savefig.facecolor': 'white',
'savefig.format': 'png',
'savefig.frameon': True,
'savefig.jpeg_quality': 95,
'savefig.orientation': 'portrait',
'savefig.pad_inches': 0.1,
'savefig.transparent': False,
'scatter.edgecolors': 'face',
'scatter.marker': 'o',
'svg.fonttype': 'path',
'svg.hashsalt': None,
'svg.image_inline': True,
'text.antialiased': True,
'text.color': 'black',
'text.hinting': 'auto',
'text.hinting_factor': 8,
'text.kerning_factor': 0,
'text.latex.preamble': '',
'text.latex.preview': False,
'text.latex.unicode': True,
'text.usetex': False,
'timezone': 'UTC',
'tk.window_focus': False,
'toolbar': 'toolbar2',
'verbose.fileo': 'sys.stdout',
'verbose.level': 'silent',
'webagg.address': '127.0.0.1',
'webagg.open_in_browser': True,
'webagg.port': 8988,
'webagg.port_retries': 50,
'xtick.alignment': 'center',
'xtick.bottom': True,
'xtick.color': 'black',
'xtick.direction': 'out',
'xtick.labelbottom': True,
'xtick.labelsize': 'medium',
'xtick.labeltop': False,
'xtick.major.bottom': True,
'xtick.major.pad': 3.5,
'xtick.major.size': 3.5,
'xtick.major.top': True,
'xtick.major.width': 0.8,
'xtick.minor.bottom': True,
'xtick.minor.pad': 3.4,
'xtick.minor.size': 2.0,
'xtick.minor.top': True,
'xtick.minor.visible': False,
'xtick.minor.width': 0.6,
'xtick.top': False,
'ytick.alignment': 'center_baseline',
'ytick.color': 'black',
'ytick.direction': 'out',
'ytick.labelleft': True,
'ytick.labelright': False,
'ytick.labelsize': 'medium',
'ytick.left': True,
'ytick.major.left': True,
'ytick.major.pad': 3.5,
'ytick.major.right': True,
'ytick.major.size': 3.5,
'ytick.major.width': 0.8,
'ytick.minor.left': True,
'ytick.minor.pad': 3.4,
'ytick.minor.right': True,
'ytick.minor.size': 2.0,
'ytick.minor.visible': False,
'ytick.minor.width': 0.6,
'ytick.right': False}))
train = pd.read_csv('train.csv')
train.shape
#shape()函数返回矩阵的规模
(891, 12)
train.head()
PassengerId | Survived | Pclass | Name | Sex | Age | SibSp | Parch | Ticket | Fare | Cabin | Embarked | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | 1 | 0 | 3 | Braund, Mr. Owen Harris | male | 22.0 | 1 | 0 | A/5 21171 | 7.2500 | NaN | S |
1 | 2 | 1 | 1 | Cumings, Mrs. John Bradley (Florence Briggs Th... | female | 38.0 | 1 | 0 | PC 17599 | 71.2833 | C85 | C |
2 | 3 | 1 | 3 | Heikkinen, Miss. Laina | female | 26.0 | 0 | 0 | STON/O2. 3101282 | 7.9250 | NaN | S |
3 | 4 | 1 | 1 | Futrelle, Mrs. Jacques Heath (Lily May Peel) | female | 35.0 | 1 | 0 | 113803 | 53.1000 | C123 | S |
4 | 5 | 0 | 3 | Allen, Mr. William Henry | male | 35.0 | 0 | 0 | 373450 | 8.0500 | NaN | S |
data = pd.read_csv('clear_data.csv')
#clear_data.cs中为清洗过的数据。
data.head()
PassengerId | Pclass | Age | SibSp | Parch | Fare | Sex_female | Sex_male | Embarked_C | Embarked_Q | Embarked_S | |
---|---|---|---|---|---|---|---|---|---|---|---|
0 | 0 | 3 | 22.0 | 1 | 0 | 7.2500 | 0 | 1 | 0 | 0 | 1 |
1 | 1 | 1 | 38.0 | 1 | 0 | 71.2833 | 1 | 0 | 1 | 0 | 0 |
2 | 2 | 3 | 26.0 | 0 | 0 | 7.9250 | 1 | 0 | 0 | 0 | 1 |
3 | 3 | 1 | 35.0 | 1 | 0 | 53.1000 | 1 | 0 | 0 | 0 | 1 |
4 | 4 | 3 | 35.0 | 0 | 0 | 8.0500 | 0 | 1 | 0 | 0 | 1 |
2、模型搭建
1)切割训练集和测试集
# sklearn模型算法选择路径图
Image('sklearn.png')
[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-52koop84-1598629059855)(output_11_0.png)]
from sklearn.model_selection import train_test_split
#train_test_split是sklearn中用于划分数据集,即将原始数据集划分成测试集和训练集两部分的函数。
#训练集用来估计模型中的参数,使模型能够反映现实,进而预测未来或其他未知的信息,而测试集用来评估模型的预测性能(预测的准确程度)。
# 一般先取出X和y后再切割,有些情况会使用到未切割的,这时候X和y就可以用,x是清洗好的数据,y是我们要预测的存活数据'Survived'
X = data
y = train['Survived']
# 对数据集进行切割
X_train, X_test, y_train, y_test = train_test_split(X, y, stratify=y, random_state=0)
#train_test_split参数:X_train,X_test, y_train, y_test =sklearn.model_selection.train_test_split(train_data,train_target,test_size=0.4, random_state=0,stratify=y_train)
# train_data:所要划分的样本特征集
# train_target:所要划分的样本结果
# test_size:样本占比,如果是整数的话就是样本的数量
# random_state:是随机数的种子。
#随机数种子:其实就是该组随机数的编号,在需要重复试验的时候,保证得到一组一样的随机数。比如你每次都填1,其他参数一样的情况下你得到的随机数组是一样的。但填0或不填,每次都会不一样。
#x,y是原始的数据集。X_train,y_train 是原始数据集划分出来作为训练模型的,fit模型的时候用。
#X_test,y_test 这部分的数据不参与模型的训练,而是用于评价训练出来的模型好坏,score评分的时候用。
#将stratify=X就是按照X中的比例分配 ,将stratify=y就是按照y中的比例分配 。
# 查看数据形状
X_train.shape, X_test.shape
((668, 11), (223, 11))
2)模型创建
from sklearn.linear_model import LogisticRegression
from sklearn.ensemble import RandomForestClassifier
#LogisticRegression为逻辑回归模型。
#RandomForestClassifier随机森林分类器,以多者为胜。
#sklearn.linear_model是用来进行线性回归的一个library。
# 默认参数逻辑回归模型
lr = LogisticRegression()
lr.fit(X_train, y_train)
#填入X\Y两个训练集。
D:\anaconda\lib\site-packages\sklearn\linear_model\_logistic.py:762: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
LogisticRegression()
# 查看训练集和测试集score值
print("Training set score: {:.2f}".format(lr.score(X_train, y_train)))
print("Testing set score: {:.2f}".format(lr.score(X_test, y_test)))
Training set score: 0.80
Testing set score: 0.79
# 调整参数后的逻辑回归模型
lr2 = LogisticRegression(C=100)
lr2.fit(X_train, y_train)
#C:浮点型,默认:1.0;其值等于正则化强度的倒数,为正的浮点数。数值越小表示正则化越强。
D:\anaconda\lib\site-packages\sklearn\linear_model\_logistic.py:762: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
LogisticRegression(C=100)
print("Training set score: {:.2f}".format(lr2.score(X_train, y_train)))
print("Testing set score: {:.2f}".format(lr2.score(X_test, y_test)))
Training set score: 0.79
Testing set score: 0.78
# 默认参数的随机森林分类模型
rfc = RandomForestClassifier()
rfc.fit(X_train, y_train)
RandomForestClassifier()
print("Training set score: {:.2f}".format(rfc.score(X_train, y_train)))
print("Testing set score: {:.2f}".format(rfc.score(X_test, y_test)))
#过拟合。
Training set score: 1.00
Testing set score: 0.83
# 调整参数后的随机森林分类模型
rfc2 = RandomForestClassifier(n_estimators=100, max_depth=5)
rfc2.fit(X_train, y_train)
RandomForestClassifier(max_depth=5)
print("Training set score: {:.2f}".format(rfc2.score(X_train, y_train)))
print("Testing set score: {:.2f}".format(rfc2.score(X_test, y_test)))
Training set score: 0.86
Testing set score: 0.80
3、输出结果
# 预测标签
pred = lr.predict(X_train)
#predict是训练后返回预测结果,是标签值。
# 此时我们可以看到0和1的数组
pred[:10]
#取出前10个标签。
array([0, 1, 1, 1, 0, 0, 1, 0, 1, 1], dtype=int64)
# 预测标签概率
pred_proba = lr.predict_proba(X_train)
#predict_proba返回的是一个 n 行 k 列的数组, 第 i 行 第 j 列上的数值是模型预测 第 i 个预测样本为某个标签的概率,并且每一行的概率和为1。
pred_proba[:10]
array([[0.60729586, 0.39270414],
[0.18238096, 0.81761904],
[0.42258598, 0.57741402],
[0.19331014, 0.80668986],
[0.8793502 , 0.1206498 ],
[0.91331757, 0.08668243],
[0.13394337, 0.86605663],
[0.90560106, 0.09439894],
[0.05273676, 0.94726324],
[0.10973509, 0.89026491]])
4、评估
1)交叉验证
#提示:交叉验证
Image('Snipaste_2020-01-05_16-37-56.png')
#预加载图片的函数。
#10项中每个值进行替换,然后进行验证,验证10次。
[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-TTta8srU-1598629059860)(output_33_0.png)]
from sklearn.model_selection import cross_val_score
#sklearn.model_selection.cross_val_score(estimator, X, y=None, groups=None, scoring=None, cv=’warn’, n_jobs=None, verbose=0, fit_params=None, pre_dispatch=‘2*n_jobs’, error_score=’raise-deprecating’)
#estimator: 需要使用交叉验证的算法
#X:输入样本数据
#y:样本标签
#groups: 将数据集分割为训练/测试集时使用的样本的组标签(一般用不到)
#scoring: 交叉验证最重要的就是他的验证方式,选择不同的评价方法,会产生不同的评价结果。具体可用哪些评价指标,官方已给出详细解释,链接:https://scikit-learn.org/stable/modules/model_evaluation.html#scoring-parameter
#cv: 交叉验证折数或可迭代的次数(迭代是指重新验证)
#n_jobs: 同时工作的cpu个数(-1代表全部)
#verbose: 详细程度
#fit_params: 传递给估计器(验证算法)的拟合方法的参数
#pre_dispatch: 控制并行执行期间调度的作业数量。减少这个数量对于避免在CPU发送更多作业时CPU内存消耗的扩大是有用的。
lr = LogisticRegression(C=100)
scores = cross_val_score(lr, X_train, y_train, cv=10)
D:\anaconda\lib\site-packages\sklearn\linear_model\_logistic.py:762: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
D:\anaconda\lib\site-packages\sklearn\linear_model\_logistic.py:762: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
D:\anaconda\lib\site-packages\sklearn\linear_model\_logistic.py:762: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
D:\anaconda\lib\site-packages\sklearn\linear_model\_logistic.py:762: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
D:\anaconda\lib\site-packages\sklearn\linear_model\_logistic.py:762: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
D:\anaconda\lib\site-packages\sklearn\linear_model\_logistic.py:762: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
D:\anaconda\lib\site-packages\sklearn\linear_model\_logistic.py:762: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
D:\anaconda\lib\site-packages\sklearn\linear_model\_logistic.py:762: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
D:\anaconda\lib\site-packages\sklearn\linear_model\_logistic.py:762: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
D:\anaconda\lib\site-packages\sklearn\linear_model\_logistic.py:762: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
# k折交叉验证分数
scores
#与真实的数据比一下。
array([0.82089552, 0.74626866, 0.74626866, 0.80597015, 0.86567164,
0.8358209 , 0.76119403, 0.82089552, 0.74242424, 0.74242424])
# 平均交叉验证分数
print("Average cross-validation score: {:.2f}".format(scores.mean()))
Average cross-validation score: 0.79
2)混淆矩阵
#提示:混淆矩阵
Image('Snipaste_2020-01-05_16-38-26.png')
[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-TdP5GY9Z-1598629059862)(output_39_0.png)]
#提示:准确率 (Accuracy),精确度(Precision),Recall,f-分数计算方法
Image('Snipaste_2020-01-05_16-39-27.png')
[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-rZnQqORy-1598629059864)(output_40_0.png)]
from sklearn.metrics import confusion_matrix
# 训练模型
lr = LogisticRegression(C=100)
lr.fit(X_train, y_train)
D:\anaconda\lib\site-packages\sklearn\linear_model\_logistic.py:762: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
n_iter_i = _check_optimize_result(
LogisticRegression(C=100)
# 模型预测结果
pred = lr.predict(X_train)
# 混淆矩阵
confusion_matrix(y_train, pred)
array([[354, 58],
[ 83, 173]], dtype=int64)
from sklearn.metrics import classification_report
# 精确率、召回率以及f1-score
print(classification_report(y_train, pred))
precision recall f1-score support
0 0.81 0.86 0.83 412
1 0.75 0.68 0.71 256
accuracy 0.79 668
macro avg 0.78 0.77 0.77 668
weighted avg 0.79 0.79 0.79 668
3)ROC曲线
from sklearn.metrics import roc_curve
fpr, tpr, thresholds = roc_curve(y_test, lr.decision_function(X_test))
plt.plot(fpr, tpr, label="ROC Curve")
plt.xlabel("FPR")
plt.ylabel("TPR (recall)")
# 找到最接近于0的阈值
close_zero = np.argmin(np.abs(thresholds))
plt.plot(fpr[close_zero], tpr[close_zero], 'o', markersize=10, label="threshold zero", fillstyle="none", c='k', mew=2)
plt.legend(loc=4)
<matplotlib.legend.Legend at 0x242d08bea30>
[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-XxfsVbQf-1598629059865)(output_49_1.png)]