3 Python数据处理及可视化

从小例子起步-——Numpy的初步使用
程序3-1：

import numpy as np
data = np.mat([[1,200,105,3,False],[2,165,80,2,False],
              [3,184.5,120,2,False],[4,116,70.8,1,False],[5,270,150,4,True]])
row = 0
for line in data:
    row += 1
print( row	)
print( data.size	)

结果：

5
25

程序3-2：

import numpy as np
data = np.mat([[1,200,105,3,False],[2,165,80,2,False],
               [3,184.5,120,2,False],[4,116,70.8,1,False],[5,270,150,4,True]])
print( print( data[0,3]))
print( print( data[0,4]))

结果：

3.0
None
0.0
None

程序3-3：

import numpy as np
data = np.mat([[1,200,105,3,False],[2,165,80,2,False],
               [3,184.5,120,2,False],[4,116,70.8,1,False],[5,270,150,4,True]])

col1 = []#空数据
for row in data:
    col1.append(row[0,1])

print( np.sum(col1))#和
print( np.mean(col1))#均值
print( np.std(col1))#标准差
print( np.var(col1))#方差

结果：

935.5
187.1
50.17808286493218
2517.84

图形化数据处理——Matplotlib包的使用
程序3-4：

import numpy as np
import pylab
import scipy.stats as stats

data = np.mat([[1,200,105,3,False],[2,165,80,2,False],
               [3,184.5,120,2,False],[4,116,70.8,1,False],[5,270,150,4,True]])

col1 = []
for row in data:
    col1.append(row[0,1])

stats.probplot(col1,plot=pylab)
pylab.show()

结果：

程序3-5：

import pandas as pd
import matplotlib.pyplot as plot
rocksVMines = pd.DataFrame([[1,200,105,3,False],[2,165,80,2,False],
               [3,184.5,120,2,False],[4,116,70.8,1,False],[5,270,150,4,True]])

dataRow1 = rocksVMines.iloc[1,0:3]
dataRow2 = rocksVMines.iloc[2,0:3]
plot.scatter(dataRow1, dataRow2)
plot.xlabel("Attribute1")
plot.ylabel(("Attribute2"))
plot.show()

dataRow3 = rocksVMines.iloc[3,0:3]
plot.scatter(dataRow2, dataRow3)
plot.xlabel("Attribute2")
plot.ylabel("Attribute3")
plot.show()

结果：


程序3-6：

import pandas as pd
import matplotlib.pyplot as plot

filePath = ("dataTest.csv")
dataFile = pd.read_csv(filePath, header=None, prefix="V")

dataRow1 = dataFile.iloc[100, 1:300]
dataRow2 = dataFile.iloc[101, 1:300]
plot.scatter(dataRow1, dataRow2)
plot.xlabel("Attribute1")
plot.ylabel("Attribute2")
plot.show()

结果：

程序3-7：

import pandas as pd
import matplotlib.pyplot as plot

filePath = ("dataTest.csv")
dataFile = pd.read_csv(filePath, header=None, prefix="V")

target = []
for i in range(200):
    if dataFile.iat[i, 10] >= 7:
        target.append(1.0)
    else:
        target.append(0.0)

dataRow = dataFile.iloc[0:200, 10]
plot.scatter(dataRow, target)
plot.xlabel("Attribute")
plot.ylabel("Target")
plot.show()

结果：

程序3-8：

import pandas as pd
import matplotlib.pyplot as plot
import numpy.random as np

filePath = ("dataTest.csv")
dataFile = pd.read_csv(filePath, header=None, prefix="V")

target = []
for i in range(200):
    if dataFile.iat[i, 10] >= 7:
        target.append(1.0 + np.uniform(-0.3, 0.3))
    else:
        target.append(0.0 + np.uniform(-0.3, 0.3))
dataRow = dataFile.iloc[0:200, 10]
plot.scatter(dataRow, target, alpha=0.5, s=100)
plot.xlabel("Attribute")
plot.ylabel("Target")
plot.show()

结果：

数据的统计学可视化展示

程序3-9：

from pylab import *
import pandas as pd
import matplotlib.pyplot as plot

filePath = ("dataTest.csv")
dataFile = pd.read_csv(filePath, header=None, prefix="V")

print(dataFile.head())
print((dataFile.tail()))

summary = dataFile.describe()#对数据进行统计学估计
print(summary)

array = dataFile.iloc[:, 10:16].values
boxplot(array)
plot.xlabel("Attribute")
plot.ylabel(("Score"))
show()

结果：

      V0    V1    V2    V3    V4  ...  V1134  V1135  V1136  V1137  V1138
0  20001  6.15  7.06  5.24  2.61  ...      7      3      6      8     12
1  20002  6.53  6.15  9.85  4.03  ...      7      1      8      1     24
2  20003  8.22  3.23  1.69  0.41  ...      8      8      1      7      6
3  20004  6.79  4.99  1.50  2.85  ...      8      1      6      5     12
4  20005 -1.00 -1.00 -1.00 -1.00  ...      8      1      8      8      1

[5 rows x 1139 columns]
        V0    V1    V2    V3    V4  ...  V1134  V1135  V1136  V1137  V1138
196  20197  3.59  5.63  6.21  5.24  ...      8      9      8      4     28
197  20198  7.27  5.31  9.35  2.77  ...      8     24      7      8     14
198  20199  6.18  5.05  6.43  6.05  ...      7      3      3      7      4
199  20200  6.12  7.45  1.05  1.03  ...      7      6      8      7     12
200  20201  5.60  6.29  6.11  2.64  ...      8      1      2      7     23

[5 rows x 1139 columns]
                 V0          V1          V2  ...       V1136       V1137       V1138
count    201.000000  201.000000  201.000000  ...  201.000000  201.000000  201.000000
mean   20101.000000    5.266219    6.447015  ...    5.631841    5.572139   16.776119
std       58.167861    2.273933    2.443789  ...    2.510733    2.517145    8.507916
min    20001.000000   -1.000000   -1.000000  ...    1.000000    1.000000    1.000000
25%    20051.000000    4.130000    5.190000  ...    3.000000    4.000000   11.000000
50%    20101.000000    5.240000    6.410000  ...    7.000000    7.000000   17.000000
75%    20151.000000    6.590000    7.790000  ...    8.000000    7.000000   23.000000
max    20201.000000   13.150000   13.960000  ...    8.000000    8.000000   33.000000

[8 rows x 1139 columns]

程序3-10：

from pylab import *
import pandas as pd
import matplotlib.pyplot as plot

filePath = ("dataTest.csv")
dataFile = pd.read_csv(filePath, header=None, prefix="V")

summary = dataFile.describe()
dataFileNormalized = dataFile.iloc[:, 1:6]
for i in range(5):
    mean = summary.iloc[1, i]
    sd = summary.iloc[2, i]

dataFileNormalized.iloc[:, i:(i + 1)] = (dataFileNormalized.iloc[:, i:(i + 1)] - mean) / sd#标准差标准化
array = dataFileNormalized.values
boxplot(array)
plot.xlabel("Attribute")
plot.ylabel(("Score"))
show()

结果：

程序3-11：

from pylab import *
import pandas as pd
import matplotlib.pyplot as plot

filePath = ("dataTest.csv")
dataFile = pd.read_csv(filePath, header=None, prefix="V")

summary = dataFile.describe()
minRings = -1#计算的最小值
maxRings = 99#计算的最大值
nrows = 10#目标行数，前10行
for i in range(nrows):
    dataRow = dataFile.iloc[i, 1:10]
    labelColor = (dataFile.iloc[i, 10] - minRings) / (maxRings - minRings)
    dataRow.plot(color=plot.cm.RdYlBu(labelColor), alpha=0.5)
plot.xlabel("Attribute")
plot.ylabel("Score")
show()

结果：

程序3-12：

from pylab import *
import pandas as pd
import matplotlib.pyplot as plot

filePath = ("dataTest.csv")
dataFile = pd.read_csv(filePath, header=None, prefix="V")

summary = dataFile.describe()
corMat = pd.DataFrame(dataFile.iloc[1:20, 1:20].corr())

plot.pcolor(corMat)
plot.show()

结果：

Python数据分析与可视化实战——某地降水的关系处理

程序3-13：

#不同年份的相同月份统计
from pylab import *
import pandas as pd
import matplotlib.pyplot as plot

filePath = ("rain.csv")
dataFile = pd.read_csv(filePath)

summary = dataFile.describe()
print(summary)

array = dataFile.iloc[:, 1:13].values
boxplot(array)
plot.xlabel("month")
plot.ylabel(("rain"))
show()

结果：

 Unnamed: 0           1           2  ...           10          11          12
count    12.000000   12.000000   12.000000  ...    12.000000   12.000000   12.000000
mean   2005.500000  121.083333   67.833333  ...  1219.250000  159.333333   38.333333
std       3.605551  103.021144   72.148626  ...   743.534938  124.611639   34.494620
min    2000.000000    0.000000    0.000000  ...   328.000000    0.000000    0.000000
25%    2002.750000   17.750000    9.750000  ...   612.250000   64.000000   18.750000
50%    2005.500000  125.000000   39.500000  ...  1208.500000  123.000000   25.500000
75%    2008.250000  204.500000  123.250000  ...  1672.250000  278.250000   46.250000
max    2011.000000  295.000000  192.000000  ...  2561.000000  357.000000  100.000000

[8 rows x 13 columns]

程序3-14：

#不同月份之间的增减程度比较
from pylab import *
import pandas as pd
import matplotlib.pyplot as plot

filePath = ("rain.csv")
dataFile = pd.read_csv(filePath)

summary = dataFile.describe()
minRings = -1
maxRings = 99
nrows = 11
for i in range(nrows):
    dataRow = dataFile.iloc[i, 1:13]
    labelColor = (dataFile.iloc[i, 12] - minRings) / (maxRings - minRings)
    dataRow.plot(color=plot.cm.RdYlBu(labelColor), alpha=0.5)
plot.xlabel("Attribute")
plot.ylabel(("Score"))
show()

结果：

程序3-15：

#每月降水是否相关
from pylab import *
import pandas as pd
import matplotlib.pyplot as plot

filePath = ("dataTest.csv")
dataFile = pd.read_csv(filePath)

summary = dataFile.describe()
corMat = pd.DataFrame(dataFile.iloc[1:20, 1:20].corr())

plot.pcolor(corMat)
plot.show()

结果：