

In [2]:

    
from sklearn import decomposition
from sklearn import datasets



In [3]:

    
import numpy as np
import matplotlib.pyplot as plt
from mpl_toolkits.mplot3d import Axes3D



In [4]:

    
np.random.seed(5)

centers = [[1, 1], [-1, -1], [1, -1]]
iris = datasets.load_iris()
X = iris.data
y = iris.target



In [5]:

    
X









    Out[5]:





array([[ 5.1,  3.5,  1.4,  0.2],
       [ 4.9,  3. ,  1.4,  0.2],
       [ 4.7,  3.2,  1.3,  0.2],
       [ 4.6,  3.1,  1.5,  0.2],
       [ 5. ,  3.6,  1.4,  0.2],
       [ 5.4,  3.9,  1.7,  0.4],
       [ 4.6,  3.4,  1.4,  0.3],
       [ 5. ,  3.4,  1.5,  0.2],
       [ 4.4,  2.9,  1.4,  0.2],
       [ 4.9,  3.1,  1.5,  0.1],
       [ 5.4,  3.7,  1.5,  0.2],
       [ 4.8,  3.4,  1.6,  0.2],
       [ 4.8,  3. ,  1.4,  0.1],
       [ 4.3,  3. ,  1.1,  0.1],
       [ 5.8,  4. ,  1.2,  0.2],
       [ 5.7,  4.4,  1.5,  0.4],
       [ 5.4,  3.9,  1.3,  0.4],
       [ 5.1,  3.5,  1.4,  0.3],
       [ 5.7,  3.8,  1.7,  0.3],
       [ 5.1,  3.8,  1.5,  0.3],
       [ 5.4,  3.4,  1.7,  0.2],
       [ 5.1,  3.7,  1.5,  0.4],
       [ 4.6,  3.6,  1. ,  0.2],
       [ 5.1,  3.3,  1.7,  0.5],
       [ 4.8,  3.4,  1.9,  0.2],
       [ 5. ,  3. ,  1.6,  0.2],
       [ 5. ,  3.4,  1.6,  0.4],
       [ 5.2,  3.5,  1.5,  0.2],
       [ 5.2,  3.4,  1.4,  0.2],
       [ 4.7,  3.2,  1.6,  0.2],
       [ 4.8,  3.1,  1.6,  0.2],
       [ 5.4,  3.4,  1.5,  0.4],
       [ 5.2,  4.1,  1.5,  0.1],
       [ 5.5,  4.2,  1.4,  0.2],
       [ 4.9,  3.1,  1.5,  0.1],
       [ 5. ,  3.2,  1.2,  0.2],
       [ 5.5,  3.5,  1.3,  0.2],
       [ 4.9,  3.1,  1.5,  0.1],
       [ 4.4,  3. ,  1.3,  0.2],
       [ 5.1,  3.4,  1.5,  0.2],
       [ 5. ,  3.5,  1.3,  0.3],
       [ 4.5,  2.3,  1.3,  0.3],
       [ 4.4,  3.2,  1.3,  0.2],
       [ 5. ,  3.5,  1.6,  0.6],
       [ 5.1,  3.8,  1.9,  0.4],
       [ 4.8,  3. ,  1.4,  0.3],
       [ 5.1,  3.8,  1.6,  0.2],
       [ 4.6,  3.2,  1.4,  0.2],
       [ 5.3,  3.7,  1.5,  0.2],
       [ 5. ,  3.3,  1.4,  0.2],
       [ 7. ,  3.2,  4.7,  1.4],
       [ 6.4,  3.2,  4.5,  1.5],
       [ 6.9,  3.1,  4.9,  1.5],
       [ 5.5,  2.3,  4. ,  1.3],
       [ 6.5,  2.8,  4.6,  1.5],
       [ 5.7,  2.8,  4.5,  1.3],
       [ 6.3,  3.3,  4.7,  1.6],
       [ 4.9,  2.4,  3.3,  1. ],
       [ 6.6,  2.9,  4.6,  1.3],
       [ 5.2,  2.7,  3.9,  1.4],
       [ 5. ,  2. ,  3.5,  1. ],
       [ 5.9,  3. ,  4.2,  1.5],
       [ 6. ,  2.2,  4. ,  1. ],
       [ 6.1,  2.9,  4.7,  1.4],
       [ 5.6,  2.9,  3.6,  1.3],
       [ 6.7,  3.1,  4.4,  1.4],
       [ 5.6,  3. ,  4.5,  1.5],
       [ 5.8,  2.7,  4.1,  1. ],
       [ 6.2,  2.2,  4.5,  1.5],
       [ 5.6,  2.5,  3.9,  1.1],
       [ 5.9,  3.2,  4.8,  1.8],
       [ 6.1,  2.8,  4. ,  1.3],
       [ 6.3,  2.5,  4.9,  1.5],
       [ 6.1,  2.8,  4.7,  1.2],
       [ 6.4,  2.9,  4.3,  1.3],
       [ 6.6,  3. ,  4.4,  1.4],
       [ 6.8,  2.8,  4.8,  1.4],
       [ 6.7,  3. ,  5. ,  1.7],
       [ 6. ,  2.9,  4.5,  1.5],
       [ 5.7,  2.6,  3.5,  1. ],
       [ 5.5,  2.4,  3.8,  1.1],
       [ 5.5,  2.4,  3.7,  1. ],
       [ 5.8,  2.7,  3.9,  1.2],
       [ 6. ,  2.7,  5.1,  1.6],
       [ 5.4,  3. ,  4.5,  1.5],
       [ 6. ,  3.4,  4.5,  1.6],
       [ 6.7,  3.1,  4.7,  1.5],
       [ 6.3,  2.3,  4.4,  1.3],
       [ 5.6,  3. ,  4.1,  1.3],
       [ 5.5,  2.5,  4. ,  1.3],
       [ 5.5,  2.6,  4.4,  1.2],
       [ 6.1,  3. ,  4.6,  1.4],
       [ 5.8,  2.6,  4. ,  1.2],
       [ 5. ,  2.3,  3.3,  1. ],
       [ 5.6,  2.7,  4.2,  1.3],
       [ 5.7,  3. ,  4.2,  1.2],
       [ 5.7,  2.9,  4.2,  1.3],
       [ 6.2,  2.9,  4.3,  1.3],
       [ 5.1,  2.5,  3. ,  1.1],
       [ 5.7,  2.8,  4.1,  1.3],
       [ 6.3,  3.3,  6. ,  2.5],
       [ 5.8,  2.7,  5.1,  1.9],
       [ 7.1,  3. ,  5.9,  2.1],
       [ 6.3,  2.9,  5.6,  1.8],
       [ 6.5,  3. ,  5.8,  2.2],
       [ 7.6,  3. ,  6.6,  2.1],
       [ 4.9,  2.5,  4.5,  1.7],
       [ 7.3,  2.9,  6.3,  1.8],
       [ 6.7,  2.5,  5.8,  1.8],
       [ 7.2,  3.6,  6.1,  2.5],
       [ 6.5,  3.2,  5.1,  2. ],
       [ 6.4,  2.7,  5.3,  1.9],
       [ 6.8,  3. ,  5.5,  2.1],
       [ 5.7,  2.5,  5. ,  2. ],
       [ 5.8,  2.8,  5.1,  2.4],
       [ 6.4,  3.2,  5.3,  2.3],
       [ 6.5,  3. ,  5.5,  1.8],
       [ 7.7,  3.8,  6.7,  2.2],
       [ 7.7,  2.6,  6.9,  2.3],
       [ 6. ,  2.2,  5. ,  1.5],
       [ 6.9,  3.2,  5.7,  2.3],
       [ 5.6,  2.8,  4.9,  2. ],
       [ 7.7,  2.8,  6.7,  2. ],
       [ 6.3,  2.7,  4.9,  1.8],
       [ 6.7,  3.3,  5.7,  2.1],
       [ 7.2,  3.2,  6. ,  1.8],
       [ 6.2,  2.8,  4.8,  1.8],
       [ 6.1,  3. ,  4.9,  1.8],
       [ 6.4,  2.8,  5.6,  2.1],
       [ 7.2,  3. ,  5.8,  1.6],
       [ 7.4,  2.8,  6.1,  1.9],
       [ 7.9,  3.8,  6.4,  2. ],
       [ 6.4,  2.8,  5.6,  2.2],
       [ 6.3,  2.8,  5.1,  1.5],
       [ 6.1,  2.6,  5.6,  1.4],
       [ 7.7,  3. ,  6.1,  2.3],
       [ 6.3,  3.4,  5.6,  2.4],
       [ 6.4,  3.1,  5.5,  1.8],
       [ 6. ,  3. ,  4.8,  1.8],
       [ 6.9,  3.1,  5.4,  2.1],
       [ 6.7,  3.1,  5.6,  2.4],
       [ 6.9,  3.1,  5.1,  2.3],
       [ 5.8,  2.7,  5.1,  1.9],
       [ 6.8,  3.2,  5.9,  2.3],
       [ 6.7,  3.3,  5.7,  2.5],
       [ 6.7,  3. ,  5.2,  2.3],
       [ 6.3,  2.5,  5. ,  1.9],
       [ 6.5,  3. ,  5.2,  2. ],
       [ 6.2,  3.4,  5.4,  2.3],
       [ 5.9,  3. ,  5.1,  1.8]])



In [7]:

    
y









    Out[7]:





array([0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
       1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
       1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
       2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
       2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2])



In [9]:

    
import pandas as pd



In [10]:

    
adult=pd.read_csv("https://archive.ics.uci.edu/ml/machine-learning-databases/adult/adult.data",header=None)



In [11]:

    
adult.columns=["age ",
"workclass ",
"fnlwgt",
"education ",
"education-num",
"marital-status",
"occupation",
"relationship",
"race",
"sex",
"capital-gain",
"capital-loss",
"hours-per-week",
"native-country",
"income",
]



In [16]:

    
adult.dtypes









    Out[16]:





age                int64
workclass         object
fnlwgt             int64
education         object
education-num      int64
marital-status    object
occupation        object
relationship      object
race              object
sex               object
capital-gain       int64
capital-loss       int64
hours-per-week     int64
native-country    object
income            object
dtype: object



In [13]:

    
y=adult.income.values
y









    Out[13]:





array([' <=50K', ' <=50K', ' <=50K', ..., ' <=50K', ' <=50K', ' >50K'], dtype=object)



In [17]:

    
#Only numeric data for PCA
X=adult[["age ","fnlwgt","education-num","capital-gain","capital-loss","hours-per-week"]].values
X









    Out[17]:





array([[    39,  77516,     13,   2174,      0,     40],
       [    50,  83311,     13,      0,      0,     13],
       [    38, 215646,      9,      0,      0,     40],
       ..., 
       [    58, 151910,      9,      0,      0,     40],
       [    22, 201490,      9,      0,      0,     20],
       [    52, 287927,      9,  15024,      0,     40]], dtype=int64)

fig = plt.figure(1, figsize=(4, 3)) plt.clf() ax = Axes3D(fig, rect=[0, 0, .95, 1], elev=48, azim=134) plt.cla()



In [18]:

    
pca = decomposition.PCA(n_components=3)
pca.fit(X)
X = pca.transform(X)



In [19]:

    
X









    Out[19]:





array([[ -1.12262330e+05,   1.09991722e+03,  -8.97964130e+01],
       [ -1.06467396e+05,  -1.07425781e+03,  -9.33540711e+01],
       [  2.58676042e+04,  -1.07828362e+03,  -8.81578195e+01],
       ..., 
       [ -3.78683960e+04,  -1.07634102e+03,  -9.06102320e+01],
       [  1.17116044e+04,  -1.07785772e+03,  -8.87784724e+01],
       [  9.81490602e+04,   1.39434958e+04,  -5.93208645e+01]])

for name, label in [('Setosa', 0), ('Versicolour', 1), ('Virginica', 2)]: ax.text3D(X[y == label, 0].mean(), X[y == label, 1].mean() + 1.5, X[y == label, 2].mean(), name, horizontalalignment='center', bbox=dict(alpha=.5, edgecolor='w', facecolor='w'))

Reorder the labels to have colors matching the cluster results

y = np.choose(y, [1, 2, 0]).astype(np.float) ax.scatter(X[:, 0], X[:, 1], X[:, 2], c=y, cmap=plt.cm.spectral, edgecolor='k')

ax.w_xaxis.set_ticklabels([]) ax.w_yaxis.set_ticklabels([]) ax.w_zaxis.set_ticklabels([])



In [20]:

    
%matplotlib inline



In [21]:

    
import seaborn as sns
iris = sns.load_dataset("iris")
sns.pairplot(iris)









    Out[21]:





<seaborn.axisgrid.PairGrid at 0x1df792df160>



In [22]:

    
import matplotlib 
import matplotlib.pyplot as plt



In [23]:

    
x=[1,2,3]
y=[5,6,9]



In [24]:

    
plt.plot(x,y)









    Out[24]:





[<matplotlib.lines.Line2D at 0x1df7ccf2908>]



In [28]:

    
plt.plot(x,y)
plt.xlabel('Customers')
plt.ylabel('Age')
plt.title('First Graph')









    Out[28]:





<matplotlib.text.Text at 0x1df7d260c50>



In [29]:

    
iris=pd.read_csv('https://raw.githubusercontent.com/vincentarelbundock/Rdatasets/master/csv/datasets/iris.csv')



In [30]:

    
iris.columns









    Out[30]:





Index(['Unnamed: 0', 'Sepal.Length', 'Sepal.Width', 'Petal.Length',
       'Petal.Width', 'Species'],
      dtype='object')



In [39]:

    
iris.columns=['Unnamed: 0', 'Sepal_Length', 'Sepal_Width', 'Petal_Length','Petal_Width', 'Species']



In [45]:

    
y=iris.groupby('Species').Sepal_Length.mean().reset_index()



In [49]:

    
y.Sepal_Length









    Out[49]:





0    5.006
1    5.936
2    6.588
Name: Sepal_Length, dtype: float64



In [50]:

    
x=iris.Species



In [55]:

    
plt.plot(iris.Sepal_Length,iris.Petal_Length)









    Out[55]:





[<matplotlib.lines.Line2D at 0x1df7e890c88>]



In [59]:

    
plt.bar(iris.Sepal_Length,iris.Petal_Length,label='bar1',color='blue')









    Out[59]:





<Container object of 150 artists>



In [62]:

    
iris.plot(x='Sepal_Length',y='Petal_Length')









    Out[62]:





<matplotlib.axes._subplots.AxesSubplot at 0x1df7f270a20>



In [67]:

    
import seaborn as sns



In [69]:

    
def sinplot(flip=1):
    x = np.linspace(0, 14, 100)
    for i in range(1, 7):
        plt.plot(x, np.sin(x + i * .5) * (7 - i) * flip)



In [70]:

    
sinplot()



In [71]:

    
diamonds=pd.read_csv('https://raw.githubusercontent.com/vincentarelbundock/Rdatasets/master/csv/Ecdat/Diamond.csv')



In [72]:

    
diamonds.head()









    Out[72]:







  
    
      
      Unnamed: 0
      carat
      colour
      clarity
      certification
      price
    
  
  
    
      0
      1
      0.30
      D
      VS2
      GIA
      1302
    
    
      1
      2
      0.30
      E
      VS1
      GIA
      1510
    
    
      2
      3
      0.30
      G
      VVS1
      GIA
      1510
    
    
      3
      4
      0.30
      G
      VS1
      GIA
      1260
    
    
      4
      5
      0.31
      D
      VS1
      GIA
      1641



In [75]:

    
diamonds=diamonds.drop( 'Unnamed: 0',1)



In [76]:

    
diamonds.head()









    Out[76]:







  
    
      
      carat
      colour
      clarity
      certification
      price
    
  
  
    
      0
      0.30
      D
      VS2
      GIA
      1302
    
    
      1
      0.30
      E
      VS1
      GIA
      1510
    
    
      2
      0.30
      G
      VVS1
      GIA
      1510
    
    
      3
      0.30
      G
      VS1
      GIA
      1260
    
    
      4
      0.31
      D
      VS1
      GIA
      1641



In [77]:

    
sns.distplot(diamonds.price,kde=True,rug=True)









    Out[77]:





<matplotlib.axes._subplots.AxesSubplot at 0x1df7f723780>



In [78]:

    
sns.kdeplot(diamonds.price,shade=True)









    Out[78]:





<matplotlib.axes._subplots.AxesSubplot at 0x1df7fd90470>



In [79]:

    
import os as os



In [80]:

    
os.getcwd()









    Out[80]:





'C:\\Users\\KOGENTIX'



In [81]:

    
os.chdir('C:\\Users\\KOGENTIX\\Desktop\\trainingWeek2')



In [83]:

    
diamonds.to_csv("diamonds2.csv")



In [84]:

    
sns.jointplot(x='price',y='carat',data=diamonds)









    Out[84]:





<seaborn.axisgrid.JointGrid at 0x1df7fdc51d0>



In [86]:

    
sns.jointplot(x='price',y='carat',kind="hex",data=diamonds)









    Out[86]:





<seaborn.axisgrid.JointGrid at 0x1df7f79e390>



In [87]:

    
sns.jointplot(x='price',y='carat',kind="kde",data=diamonds)









    Out[87]:





<seaborn.axisgrid.JointGrid at 0x1df002a26a0>



In [88]:

    
sns.pairplot(iris)









    Out[88]:





<seaborn.axisgrid.PairGrid at 0x1df01467390>



In [89]:

    
sns.pairplot(diamonds)









    Out[89]:





<seaborn.axisgrid.PairGrid at 0x1df02465748>



In [90]:

    
sns.regplot(x='price',y='carat',data=diamonds)









    Out[90]:





<matplotlib.axes._subplots.AxesSubplot at 0x1df02eba470>



In [91]:

    
sns.lmplot(x='price',y='carat',data=diamonds)









    Out[91]:





<seaborn.axisgrid.FacetGrid at 0x1df02f70cf8>



In [93]:

    
sns.lmplot(x='price',y='carat',hue='colour',data=diamonds)









    Out[93]:





<seaborn.axisgrid.FacetGrid at 0x1df02e91128>



In [94]:

    
sns.stripplot(x='colour',y='carat',data=diamonds)









    Out[94]:





<matplotlib.axes._subplots.AxesSubplot at 0x1df03187f28>



In [95]:

    
sns.stripplot(x='colour',y='price',data=diamonds)









    Out[95]:





<matplotlib.axes._subplots.AxesSubplot at 0x1df7ff01550>



In [98]:

    
sns.stripplot(x='clarity',y='price',data=diamonds)









    Out[98]:





<matplotlib.axes._subplots.AxesSubplot at 0x1df7fff26d8>



In [97]:

    
diamonds.head()









    Out[97]:







  
    
      
      carat
      colour
      clarity
      certification
      price
    
  
  
    
      0
      0.30
      D
      VS2
      GIA
      1302
    
    
      1
      0.30
      E
      VS1
      GIA
      1510
    
    
      2
      0.30
      G
      VVS1
      GIA
      1510
    
    
      3
      0.30
      G
      VS1
      GIA
      1260
    
    
      4
      0.31
      D
      VS1
      GIA
      1641



In [99]:

    
sns.swarmplot(x='clarity',y='price',data=diamonds)









    Out[99]:





<matplotlib.axes._subplots.AxesSubplot at 0x1df0003ebe0>



In [100]:

    
sns.swarmplot(x='clarity',y='price',hue='colour',data=diamonds)









    Out[100]:





<matplotlib.axes._subplots.AxesSubplot at 0x1df041e7278>



In [102]:

    
sns.boxplot(x='clarity',y='price',hue='colour',data=diamonds)









    Out[102]:





<matplotlib.axes._subplots.AxesSubplot at 0x1df04306518>



In [103]:

    
sns.boxplot(hue='clarity',y='price',x='colour',data=diamonds)









    Out[103]:





<matplotlib.axes._subplots.AxesSubplot at 0x1df047a2e80>



In [104]:

    
sns.boxplot(y='price',x='colour',data=diamonds)









    Out[104]:





<matplotlib.axes._subplots.AxesSubplot at 0x1df04c1fa58>



In [105]:

    
sns.violinplot(hue='clarity',y='price',x='colour',data=diamonds)









    Out[105]:





<matplotlib.axes._subplots.AxesSubplot at 0x1df04d66a58>



In [106]:

    
sns.violinplot(y='price',x='colour',data=diamonds)









    Out[106]:





<matplotlib.axes._subplots.AxesSubplot at 0x1df04fa60b8>



In [107]:

    
sns.barplot(hue='clarity',y='price',x='colour',data=diamonds)









    Out[107]:





<matplotlib.axes._subplots.AxesSubplot at 0x1df050f9ba8>



In [108]:

    
sns.barplot(y='price',x='colour',data=diamonds)









    Out[108]:





<matplotlib.axes._subplots.AxesSubplot at 0x1df051e0d30>



In [109]:

    
sns.countplot(x='colour',data=diamonds)









    Out[109]:





<matplotlib.axes._subplots.AxesSubplot at 0x1df0537ebe0>



In [110]:

    
sns.pointplot(hue='clarity',y='price',x='colour',data=diamonds)









    Out[110]:





<matplotlib.axes._subplots.AxesSubplot at 0x1df04325be0>



In [112]:

    
sns.factorplot(hue='clarity',x='colour',y='price',col='certification',data=diamonds)









    Out[112]:





<seaborn.axisgrid.FacetGrid at 0x1df06afdda0>



In [113]:

    
sns.factorplot(hue='clarity',x='colour',y='price',col='certification',data=diamonds,kind='bar')









    Out[113]:





<seaborn.axisgrid.FacetGrid at 0x1df06e52048>



In [ ]:

	Unnamed: 0	carat	colour	clarity	certification	price
0	1	0.30	D	VS2	GIA	1302
1	2	0.30	E	VS1	GIA	1510
2	3	0.30	G	VVS1	GIA	1510
3	4	0.30	G	VS1	GIA	1260
4	5	0.31	D	VS1	GIA	1641