Python Data Analysis I

Python Data Analysis Overview

The meaning and goal of data analysis

Statistical analysis method

Extracting useful information

Research, generalization, summary

Python and data analytics

Python:guido Van Rossum Christmas Holiday, 1989

Features: Introduction Development efficiency slow operation (relative to C + + and Java) glue characteristics (Integrated C language)

Data analysis: NumPy, scipy, matplotlib, Pandas, Scikit-learn, Keras

Python Data analytics big family

NumPy (Numeric Python): Data structure basics. is an open-source numerical computation extension of Python. This tool can be used to store and manipulate large matrices, which is much more efficient than Python's own nested list (nested list structure) structure, which is also useful for representing matrices (matrix). It is said that NumPy Python is the equivalent of becoming a free, more powerful MATLAB system.

SCIPY: Powerful Scientific Computing Methods (matrix analysis, signal and image analysis, mathematical analysis ...) ）

Matplotlib: a rich visualization suite

Pandas: Basic data Analysis suite. The tool was created to solve the data analysis task. Pandas incorporates a number of libraries and a number of standard data models, providing the tools needed to efficiently manipulate large datasets. Pandas provides a number of functions and methods that enable us to process data quickly and easily. Pandas was originally developed as a financial data analysis tool, so pandas provides a good support for time series analysis. The name of the pandas comes from panel data and Python data analysis.

Scikit-learn: A powerful data analysis modeling Library

Keras: (depth) Artificial neural network

Python Environment setup

Platforms: Windows, Linux, MacOS

Scientific Computing tools: Anaconda

Basic techniques for data analysis in Python

I. NumPy

Keywords: Open source data calculation extension

Function: Ndarray multidimensional operation linear algebra

Ndarray

#encoding=utf-8import numpy as npdef main():    lst=[[1,2,3],[2,4,6]]    print(type(lst))    np_lst=np.array(lst)    print(type(lst))    np_lst=np.array(lst,dtype=np.float)    # bool    # int,int8,int16,int32,int64,int128    # uint8,uint16,uint32,uint64,uint128,    # float16/32/64,complex64/128    print(np_lst.shape)         # 行列数    print(np_lst.ndim)          # 维数    print(np_lst.dtype)         # 数据类型    print(np_lst.itemsize)      # 每个数据的数据存储大小    print(np_lst.size)          # 元素个数

Some kinds of array

#encoding=utf-8import numpy as npdef main():    print(np.zeros([2, 4]))    print(np.ones([3, 5]))    print("Rand:")    print(np.random.rand())                 # 0-1内均匀分布随机数    print(np.random.rand(2, 4))    print("RandInt:")    print(np.random.randint(1, 10, 3))      # 3个1-10内随机分布整数    print("Randn:")    print(np.random.randn(2, 4))            # 标准正态随机数    print("Choice:")    print(np.random.choice([10, 20, 30]))   # 指定范围内的随机数    print("Distribute:")    print(np.random.beta(1, 10, 100))       # 比如Beta分布，Dirichlet分布etc

Opeartion

#encoding =utf-8import NumPy as Npdef main (): Print (Np.arange (1, one). Reshape ([2, 5]) LST = Np.arange (1, one). Reshape (    [2, 5]) Print ("EXP:") Print (Np.exp (LST)) print ("EXP2:") Print (NP.EXP2 (LST)) print ("SQRT:") Print (NP.SQRT (LST)) p                     Rint ("Sin:") Print (Np.sin (LST)) print ("Log:") Print (Np.log (LST)) LST = Np.array ([[[[[[1], 2, 3, 4], [4, 5, 6, 7]], [[7, 8, 9, 10], [10, 11, 12, 13]], [[14, 15            , [+], [+], [+]] Print (LST) print ("Sum:") print (Lst.sum ()) # all elements sum print (Lst.sum (axis=0)) # Outermost sum print (Lst.sum (Axis=1)) # Second Layer summation print (Lst.sum (axis=-1 ) # Innermost sum print ("Max:") print (Lst.max ()) Print ("Min:") print (Lst.min ()) Lst1 = Np.array ([10, 20, 30, 4 0]) Lst2 = Np.array ([4, 3, 2, 1]) print ("ADD:") print (Lst1 + lst2) print ("Sub:") print (LST1-LST2) prin    T ("Mul:")Print (LST1 * lst2) print ("Div:") print (lst1/lst2) print ("Square:") Print (LST1 * * lst2) print ("Dot:") p Rint (Np.dot (Lst1.reshape ([2, 2]), Lst2.reshape ([2, 2])) print ("Cancatenate") Print (Np.concatenate (Lst1, lst2), Axi s=0)) Print (Np.vstack ((Lst1, Lst2)) # line stitching print (Np.hstack (Lst1, Lst2)) # By column Connect print (Np.split (Lst1, 2)) # vector split print (np.copy (lst1)) # vector copy

Liner algebra

#encoding=utf-8import numpy as npfrom numpy.linalg import *def main():    ## Liner    print(np.eye(3))    lst = np.array([[1, 2],                    [3, 4]])    print("Inv:")    print(inv(lst))    print("T:")    print(lst.transpose())    print("Det:")    print(det(lst))    print("Eig:")    print(eig(lst))    y = np.array([[5], [7]])    print("Solve")    print(solve(lst, y))

Others

#encoding=utf-8import numpy as npdef main():    ## Other    print("FFT:")    print(np.fft.fft(np.array([1, 1, 1, 1, 1, 1, 1, 1, 1])))    print("Coef:")    print(np.corrcoef([1, 0, 1], [0, 2, 1]))    print("Poly:")    print(np.poly1d([2, 1, 3]))             #一元多次方程

II. matplotlib

Keywords: Drawing library

Line

#encoding =utf-8import NumPy as Npimport Matplotlib.pyplot as Pltdef Main (): # # line x = Np.linspace (-np.pi, Np.pi, 2 Endpoint=true) C, s = Np.cos (x), Np.sin (x) Plt.plot (x, C) plt.figure (1) plt.plot (x, C, color= "Blue", linew idth=1.5, linestyle= "-", label= "cos", alpha=0.6) Plt.plot (x, S, "r*", label= "SIN", alpha=0.6) plt.title ("Cos & S In ", size=16) ax = PLT.GCA () # axis editor ax.spines[" right "].set_color (" none ") ax.spines[" Top "].set_colo R ("none") ax.spines["left"].set_position (("Data", 0) ax.spines["Bottom"].set_position (("Data", 0) ax.xaxis.set_ Ticks_position ("Bottom") ax.yaxis.set_ticks_position ("left") plt.xticks ([-np.pi,-NP.PI/2, 0, NP.PI/2, Np.pi], [R ' $- \pi$ ', R ' $-\pi/2$ ', R ' $0$ ', R ' $\pi/2$ ', R ' $\pi$ ']) # Regular Expression plt.yticks (Np.linspace ( -1, 1, 5, endpoint=t Rue)) for label in Ax.get_xticklabels () +ax.get_yticklabels (): label.set_fontsize (+) Label.set_bbox (Dict ( Facecolor= "White", EDGECOlor= "None", alpha=0.2)) plt.legend (loc= "upper left") Plt.grid () # Plt.axis ([-2, 1, -0.5, 1]) # Fill: Fill the PLT . Fill_between (x, Np.abs (x) < 0.5, C, C > 0.5, color= "green", alpha=0.25) T = 1 plt.plot ([T, T], [0, Np.cos (t)] , "Y", linewidth=3, linestyle= "--") plt.annotate ("cos (1)", xy= (T, Np.cos (1)), xycoords= "Data", xytext= (+10, +30), Textco     Ords= "offset points", arrowprops=dict (arrowstyle= ", connectionstyle=" arc3,rad=.2 "))

Plt.fill_between (x, Np.abs (x) < 0.5, C, C > 0.5, color= "green", alpha=0.25)

The first parameter x represents the x-axis, the second parameter Np.abs (x) represents the absolute value of x, Np.abs (x) < 0.5 is a decision variable, C is the y-axis, and C > 0.5 is a criterion.

When Np.abs (x) < 0.5 is true (1), the y-axis of 1 (satisfying c>0.5) begins to fill both sides (of course the x-axis is the area between 0.5 and 0.5), at which point the two small blocks above the graph are filled. When Np.abs (x) >= 0.5 is False (0), it fills up from 0 of the y-axis, and of course only fills the area of the c>0.5, which is the two large symmetric regions in the diagram.

Many types of figures

#encoding =utf-8import NumPy as Npimport Matplotlib.pyplot as Pltdef Main (): Fig = Plt.figure () # # Scatter ax = fi G.add_subplot (3, 3, 1) n = X = Np.random.normal (0, 1, n) Y = np.random.normal (0, 1, n) T = np.arctan2 (Y, X # plt.axes ([0.025, 0.025, 0.95, 0.95]) Plt.scatter (X, Y, s=75, c=t, alpha=.5) Plt.xlim ( -1.5, 1.5), Plt.xticks ([ ]) Plt.ylim ( -1.5, 1.5), Plt.yticks ([]) Plt.axis () plt.title ("Scatter") Plt.xlabel ("X") Plt.ylabel ("Y") # # bar Fig.add_subplot (332) n = ten X = Np.arange (n) Y1 = (1-x/float (n)) * Np.random.uniform (0.5, 1, N) Y 2 = (1-x/float (n)) * Np.random.uniform (0.5, 1, N) plt.bar (X, +y1, facecolor= ' #9999ff ', edgecolor= ' white ') plt.ba  R (x,-y2, facecolor= ' #ff9999 ', edgecolor= ' white ') for X, y in Zip (x,y1): Plt.text (x + 0.4, y + 0.05, '%.2f '% y, Ha= ' center ', va= ' bottom ') for x, y in Zip (x,y2): Plt.text (x + 0.4,-y-0.05, '%.2f '% y, ha= ' center ', va= ' top ') # # Pie Fig.add_Subplot (333) n = z = Np.ones (n) z[-1] *= 2 # Explode sector away from center Plt.pie (Z, explode=z*.05, colors=['%f '% (i /float (n)) for I in range (n)], labels=['%.2f '% (I/float (n)) for I in range (n)]) PLT.GCA (). Set_aspect (' EQ UAL ') # round plt.xticks ([]), Plt.yticks ([]) # # Polar Fig.add_subplot (334, polar=true) n = theta = NP . Arange (0, 2 * np.pi, 2 * np.pi/n) radii = ten * Np.random.rand (n) plt.polar (theta, radii) # Plt.plot (Theta, Rad II) # # Heatmap Fig.add_subplot (335) from matplotlib import cm data = Np.random.rand (5, ten) CMap = cm. Blues map = plt.imshow (data, interpolation= ' nearest ', Cmap=cmap, aspect= ' auto ', vmin=0, vmax=1) # 3D from mpl_to    Olkits.mplot3d import Axes3d ax = Fig.add_subplot (336, projection= "3d") Ax.scatter (1, 1, 3, s=100) # # Hot Map    Fig.add_subplot (313) def f (x, Y): Return (1-x/2 + x * * 5 + y * * 3) * NP.EXP (-X * * * 2-y * 2) n = 256 x = Np.linspace ( -3, 3, n * 2)    y = Np.linspace ( -3, 3, N) X, y = Np.meshgrid (x, y) plt.contourf (x, Y, f (x, y), 8, alpha=.75, Cmap=plt.cm.hot) Plt.savefig ("./data/fig.png") Plt.show ()

Python data Analysis I