table of Contents
numpy module
numpy module: used for data analysis , for numpy array (rows have both columns) - Matrix scientific computing
When in use, use a little different from other modules
import numpy as npUse of specific methods
1. Create a numpy array --- "variable
# 一组数据相乘
import numpy as np
arr1 = np.array([1,2,3])
arr2 = np.array([4,5,6])
print(arr1*arr2)
# 输出为 [ 4 10 18]2. dimension array
# 一维数组(不在讨论范围内)
arr1 = np.array([1, 2, 4])
print(type(arr), arr1)
#输出结果为 :<class 'numpy.ndarray'> [1 2 4]
# 二维数组（******）
arr2 = np.array([
[1, 2, 3],
[4, 5, 6]
])
print(arr2)
#输出结果为 :
[[1 2 3]
[4 5 6]]
# 三维数组（不在讨论范围内）--》tensorflow
arr3 = np.array([
[[1, 2, 3],
[4, 5, 6]],
[[1, 2, 3],
[4, 5, 6]],
])
print(arr3)
#输出结果为 :
[[[1 2 3]
[4 5 6]]
[[1 2 3]
[4 5 6]]]
#T 数组的转置（对高维数组而言） --> 行列互换，转置
print(arr, '\n', arr.T)
# size 数组元素的个数
print(arr.size)
# ndim 数组的维数
print(arr.ndim)
print(arr3.ndim)
# shape 数组的维度大小（以元组形式）
print(arr.shape[0])
print(arr.shape[1])
# astype 类型转换
arr = arr.astype(np.float64)
print(arr)
# 切片numpy数组
lt = [1, 2, 3]
print(lt[:])
arr = np.array([
[1, 2, 3],
[4, 5, 6]
])
print(arr[:, :]) # 行，列
print(arr[0, 0])
print(arr[0, :])
print(arr[:, -2:])
# 逻辑取值
print(arr[arr > 4])
# 赋值
lt = [1, 2, 3]
lt[:] = [0, 0, 0]
print(lt)
arr = np.array([
[1, 2, 3],
[4, 5, 6]
])
arr[0, 0] = 0
print(arr)
arr[0, :] = 0
print(arr)
arr[:, :] = 0
print(arr)
# 数组的合并
arr1 = np.array([
[1, 2, 3],
[4, 5, 6]
])
arr2 = np.array([
[7, 8, 9],
['a', 'b', 'c']
])
print(np.hstack((arr1, arr2))) # 只能放元组
print(np.vstack((arr1, arr2)))
print(np.concatenate((arr1, arr2), axis=1)) # 默认以列合并 # 0表示列，1表示行
# 通过函数创建numpy数组
print(np.ones((2, 3)))
print(np.zeros((2, 3)))
print(np.eye(3, 3))
print(np.linspace(1, 100, 10))
print(np.arange(2, 10))
arr1 = np.zeros((1, 12))
print(arr1.reshape((3, 4))) # 重构形状
# numpy数组运算
# +-*'
arr1 = np.ones((3, 4)) * 4
print(arr1)
# numpy数组运算函数
print(np.sin(arr1))
# 矩阵运算--点乘
arr1 = np.array([
[1, 2, 3],
[4, 5, 6]
])
arr2 = np.array([
[1, 2],
[4, 5],
[6, 7]
])
# 2* 3 3*2
print(np.dot(arr1, arr2))
# 求逆
arr = np.array([[1, 2, 3], [4, 5, 6], [9, 8, 9]])
print(np.linalg.inv(arr))
# numpy数组数学和统计方法
print(np.sum(arr[0, :]))
# numpy.random生成随机数(******)
print(np.random.rand(3, 4))
print(np.random.random((3, 4)))
# np.random.seed(1)
print(np.random.random((3, 4)))
s = np.random.RandomState(1)
print(s.random((3, 4)))
arr = np.array([[1, 2, 3], [4, 5, 6], [9, 8, 9]])
np.random.shuffle(arr)
print(arr)
#仅作了解
# dtype 数组元素的数据类型,numpy数组是属于python解释器的；int32/float64属于numpy的
print(arr.dtype)
# 针对一维
print(np.random.choice([1, 2, 3], 1))
# 针对某一个范围
print(np.random.randint(1, 100, (3, 4)))ythonmatplotlib module
matplotlib module: Paint
1. Bar Chart
from matplotlib import pyplot as plt # 约定俗成
from matplotlib.font_manager import FontProperties # 修改字体
font = FontProperties(fname='C:\Windows\Fonts\simsun.ttc')
plt.style.use('ggplot') # 设置背景
clas = ['3班', '4班', '5班', '6班']
students = [50, 55, 45, 60]
clas_index = range(len(clas))
# [0,1,2,3] [50,55,45,60]
plt.bar(clas_index,students,color='darkblue')
plt.xlabel('学生',fontproperties=font)
plt.ylabel('学生人数',fontproperties=font)
plt.title('班级-学生人数',fontproperties=font,fontsize=20,fontweight=25)
plt.xticks(clas_index,clas,fontproperties=font)
plt.show()2. Histogram
import numpy as np
from matplotlib import pyplot as plt # 约定俗成
from matplotlib.font_manager import FontProperties # 修改字体
font = FontProperties(fname='C:\Windows\Fonts\simsun.ttc')
plt.style.use('ggplot')
x1 = np.random.randn(10000)
x2 = np.random.randn(10000)
fig = plt.figure() # 生成一张画布
ax1 = fig.add_subplot(1, 2, 1) # 1行2列取第一个
ax2 = fig.add_subplot(1, 2, 2)
ax1.hist(x1, bins=50,color='darkblue')
ax2.hist(x2, bins=50,color='y')
fig.suptitle('两个正太分布',fontproperties=font,fontsize=20)
ax1.set_title('x1的正太分布',fontproperties=font) # 加子标题
ax2.set_title('x2的正太分布',fontproperties=font)
plt.show()3. Line Chart
import numpy as np
from matplotlib import pyplot as plt # 约定俗成
from matplotlib.font_manager import FontProperties # 修改字体
font = FontProperties(fname='C:\Windows\Fonts\simsun.ttc')
plt.style.use('ggplot')
x1 = np.random.randn(10000)
x2 = np.random.randn(10000)
fig = plt.figure() # 生成一张画布
ax1 = fig.add_subplot(1, 2, 1) # 1行2列取第一个
ax2 = fig.add_subplot(1, 2, 2)
ax1.hist(x1, bins=50,color='darkblue')
ax2.hist(x2, bins=50,color='y')
fig.suptitle('两个正太分布',fontproperties=font,fontsize=20)
ax1.set_title('x1的正太分布',fontproperties=font) # 加子标题
ax2.set_title('x2的正太分布',fontproperties=font)
plt.show()4. FIG straight scattergram +
font = FontProperties(fname='C:\Windows\Fonts\simsun.ttc')
plt.style.use('ggplot')
fig = plt.figure()
ax1 = fig.add_subplot(1, 2, 1)
ax2 = fig.add_subplot(1, 2, 2)
x = np.arange(20)
y = x ** 2
x2 = np.arange(20)
y2 = x2
ax1.scatter(x, y, c='r', label='红')
ax1.scatter(x2, y2, c='b', label='蓝')
ax2.plot(x, y)
ax2.plot(x2, y2)
fig.suptitle('两张图', fontproperties=font, fontsize=15)
ax1.set_title('散点图', fontproperties=font)
ax2.set_title('折线图', fontproperties=font)
ax1.legend(prop=font)
plt.show()
pandas module
Features
pandas is the core module python data analysis. It provides five major functions:
- Support file access operation, support database (sql), html, json, pickle, csv (txt, excel), sas, stata, hdf like.
- Support CRUD, slice, higher-order functions, a single table packet polymerization operation, as well as and dict, list of interchangeable.
- It supports multi-table mosaic merge operation.
- It supports simple drawing operations.
- Analysis of operational support simple statistics.
Specific usage
# pd从excel中读取 DataFrame数据类型
np.random.seed(10)
index = pd.date_range('2019-01-01', periods=6, freq='M')
print(index)
columns = ['c1', 'c2', 'c3', 'c4']
print(columns)
val = np.random.randn(6, 4)
print(val)
df = pd.DataFrame(index=index, columns=columns, data=val)
print(df)
# 保存文件，读出成文件
df.to_excel('date_c.xlsx')
# 读出文件
df = pd.read_excel('date_c.xlsx', index_col=[0])
print(df)
print(df.index)
print(df.columns)
print(df.values)
print(df[['c1', 'c2']])
# 按照index取值
# print(df['2019-01-31'])
print(df.loc['2019-01-31'])
print(df.loc['2019-01-31':'2019-05-31'])
# 按照values取值
print(df)
print(df.iloc[0, 0])
df.iloc[0, :] = 0
print(df)