- 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)
- 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(data[0,3])
- print(data[0,4])
- 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(data)
- col1 = []
- for row in data:
- print(row)
- col1.append(row[0,1])
- print(col1)
- print(np.sum(col1))
- print(np.mean(col1))
- print(np.std(col1))
- print(np.var(col1))
- import pylab
- import numpy as np
- 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()
- 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]])
- print(rocksVMines)
- dataRow1 = rocksVMines.iloc[1,0:3]
- dataRow2 = rocksVMines.iloc[2,0:3]
- print(type(dataRow1))
- print(dataRow1)
- print(dataRow2)
- 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()
- import numpy as np
- import pandas as pd
- import matplotlib.pyplot as plot
- filePath = ("G:\\MyLearning\\TensorFlow_deep_learn\\data\\dataTest.csv")
- dataFile = pd.read_csv(filePath,header=None, prefix="V")
- print(np.shape(dataFile))
- dataRow1 = dataFile.iloc[100,1:300]
- dataRow2 = dataFile.iloc[101,1:300]
- plot.scatter(dataRow1, dataRow2)
- plot.xlabel("Attribute1")
- plot.ylabel("Attribute2")
- plot.show()
- import pandas as pd
- import matplotlib.pyplot as plot
- filePath = ("G:\\MyLearning\\TensorFlow_deep_learn\\data\\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()
- import random as rd
- import pandas as pd
- import matplotlib.pyplot as plot
- filePath = ("G:\\MyLearning\\TensorFlow_deep_learn\\data\\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 + rd.uniform(-0.3, 0.3))
- else:
- target.append(0.0 + rd.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()
- from pylab import *
- import pandas as pd
- import matplotlib.pyplot as plot
- filePath = ("G:\\MyLearning\\TensorFlow_deep_learn\\data\\dataTest.csv")
- dataFile = pd.read_csv(filePath,header=None, prefix="V")
- print(dataFile.head())
- print(dataFile.tail())
- summary = dataFile.describe()
- print(summary)
- array = dataFile.iloc[:,10:16].values
- boxplot(array)
- plot.xlabel("Attribute")
- plot.ylabel("Score")
- show()
来源: http://www.bubuko.com/infodetail-2946521.html