API - 机器学习 - 速查

常规操作

import numpy as np
import matplotlib as mpl
import matplotlib.pyplot as plt
import warnings
## 设置字符集，防止中文乱码
mpl.rcParams['font.sans-serif']=[u'simHei']
mpl.rcParams['axes.unicode_minus']=False
## 拦截异常
warnings.filterwarnings(action = 'ignore', category=ConvergenceWarning)

from sklearn.linear_model import LinearRegression, LassoCV, RidgeCV, ElasticNetCV
from sklearn.preprocessing import PolynomialFeatures#数据预处理，标准化
from sklearn.pipeline import Pipeline
from sklearn.linear_model.coordinate_descent import ConvergenceWarning

---

一、pandas

pandas.DataFrame.describe

---

pandas.DataFrame.dtypes

---

pandas.DataFrame.iloc
获取所有行的前两列: X = data.iloc[:,0:2]

---

二、sklearn

sklearn.preprocessing.scale
sklearn.preprocessing.StandardScale

sklearn.preprocessing.MinMaxScaler

sklearn.preprocessing.normalize
参考：技巧 - 剖析归一化和标准化

---

sklearn.pipeline.Pipeline
参考：API - Sklearn三大模型

---

sklearn.pipeline.PolynomialFeatures

---

三、numpy

numpy.arange

# np.arange(3) 输出 [0, 1, 2]
t=np.arange(len(X_test))
plt.plot(t, Y_test, 'r-', label=u'真实值', ms=10, zorder=N)

---

numpy.linspace

degree = np.arange(1, N, 4)  # 阶
colors = []  # 颜色
for c in np.linspace(16711680, 255, degree.size):
    # int(c) 转6位16进制，前补0
    colors.append('#%06x' % int(c))

---

numpy.set_printoptions

np.random.seed(100)
#显示方式设置，每行的字符数用于插入换行符，是否使用科学计数法
np.set_printoptions(linewidth=1000, suppress=True)
N = 10
x = np.linspace(0, 6, N) + np.random.randn(N)
y = 1.8*x**3 + x**2 - 14*x - 7 + np.random.randn(N)
## 将其设置为矩阵
x.shape = -1, 1
y.shape = -1, 1

参考: 确定浮点数字、数组、和numpy对象的显示形式

---

向上 - numpy.ceil
向下 - numpy.floor
四舍五入 - numpy.rint
截取整数部分 - numpy.trunc

---

四、matplotlib

matplotlib.pyplot.plot
plt.plot(x, y, 'ro', ms=10, zorder=N)
ms - 宽度 zorder - 图像的层

---

01 matplotlib - 折线图、绘图属性、Web安全色、子图、保存画板
02 matplotlib - 柱状图、直方图、散点图 、饼图