# Start writing code here...
from scipy import misc
img=misc.face()
import matplotlib.pyplot as plt
plt.imshow(img)
plt.show()
imred=img.copy()
imred[:,:,1:]=0
imred[55,0]
plt.imshow(imred)
plt.show()
img.shape
#define linear relation like y=kx+random noise
#save the data set using panda
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
x=5*np.random.rand(100)*2
y=15-4*x+np.random.rand(100)*2
plt.plot(x,y,"r.")
plt.axis([0,5,0,20])
plt.show()
df=pd.DataFrame
from sklearn.linear_model import LinearRegression
lin_reg=LinearRegression()
lin_reg.fit(x.reshape(-1,1),y)
lin_reg.intercept_+lin_reg.coef_
plt.plot(x,y,"r.")
plt.axis([0,5,0,20])
plt.plot(x,lin_reg.intercept_+lin_reg.coef_*x,"b-")
plt.show()
from sklearn.metrics import mean_squared_error as mse
y_pred=lin_reg.intercept_+lin_reg.coef_*x
mse(y,y_pred)
from sklearn.metrics import r2_score as r2
r2(y, y_pred)
lin_reg.score(x.reshape(-1,1),y)
#exercises numpy (as yesterday when I wasn't aroud)
arr = np.array((1, 2, 3, 4, 5))
print(arr)
[1 2 3 4 5]
v = np.linspace(10,-10,100)
print(v)
[ 10. 9.7979798 9.5959596 9.39393939 9.19191919
8.98989899 8.78787879 8.58585859 8.38383838 8.18181818
7.97979798 7.77777778 7.57575758 7.37373737 7.17171717
6.96969697 6.76767677 6.56565657 6.36363636 6.16161616
5.95959596 5.75757576 5.55555556 5.35353535 5.15151515
4.94949495 4.74747475 4.54545455 4.34343434 4.14141414
3.93939394 3.73737374 3.53535354 3.33333333 3.13131313
2.92929293 2.72727273 2.52525253 2.32323232 2.12121212
1.91919192 1.71717172 1.51515152 1.31313131 1.11111111
0.90909091 0.70707071 0.50505051 0.3030303 0.1010101
-0.1010101 -0.3030303 -0.50505051 -0.70707071 -0.90909091
-1.11111111 -1.31313131 -1.51515152 -1.71717172 -1.91919192
-2.12121212 -2.32323232 -2.52525253 -2.72727273 -2.92929293
-3.13131313 -3.33333333 -3.53535354 -3.73737374 -3.93939394
-4.14141414 -4.34343434 -4.54545455 -4.74747475 -4.94949495
-5.15151515 -5.35353535 -5.55555556 -5.75757576 -5.95959596
-6.16161616 -6.36363636 -6.56565657 -6.76767677 -6.96969697
-7.17171717 -7.37373737 -7.57575758 -7.77777778 -7.97979798
-8.18181818 -8.38383838 -8.58585859 -8.78787879 -8.98989899
-9.19191919 -9.39393939 -9.5959596 -9.7979798 -10. ]
#exercise 3
v1 = np.linspace(0,20)
print(v1)
[ 0. 0.40816327 0.81632653 1.2244898 1.63265306 2.04081633
2.44897959 2.85714286 3.26530612 3.67346939 4.08163265 4.48979592
4.89795918 5.30612245 5.71428571 6.12244898 6.53061224 6.93877551
7.34693878 7.75510204 8.16326531 8.57142857 8.97959184 9.3877551
9.79591837 10.20408163 10.6122449 11.02040816 11.42857143 11.83673469
12.24489796 12.65306122 13.06122449 13.46938776 13.87755102 14.28571429
14.69387755 15.10204082 15.51020408 15.91836735 16.32653061 16.73469388
17.14285714 17.55102041 17.95918367 18.36734694 18.7755102 19.18367347
19.59183673 20. ]
len(v)
v1 = np.random.randint(-10,10,4)
print('v1 = ')
print(v1)
v2 = np.random.randint(-10,10,4)
print('v2 = ')
print(v2)
r = v1*v2
print('r = ')
print(r)
v1 =
[ 8 -10 -10 0]
v2 =
[ 9 6 -6 8]
r =
[ 72 -60 60 0]
M= np.arange(1,10).reshape((3, 3))
print(M)
[[1 2 3]
[4 5 6]
[7 8 9]]
M1 = np.random.random((3,3,3))
print(M1)
[[[0.13129326 0.33184931 0.2085357 ]
[0.204677 0.20112018 0.6083181 ]
[0.87302781 0.664866 0.56535958]]
[[0.98850346 0.47940179 0.17830927]
[0.72457285 0.12145869 0.02121238]
[0.77331644 0.21381654 0.82214127]]
[[0.09098591 0.68952055 0.58342313]
[0.42301565 0.71994394 0.88838158]
[0.94224238 0.75115987 0.5162624 ]]]
x = np.random.randn(10)
print('x = ')
print(x)
print('sum of all elements:')
print(np.sum(x))
print("Sum of each column:")
print(np.sum(x, axis=0))
print("Sum of each row:")
print(np.sum(x, axis=1))
x =
[ 1.04546349 -0.41140531 0.87569544 1.12082132 0.71577783 -1.43339453
0.57592779 -1.17173327 1.58022222 -1.09851112]
sum of all elements:
1.7988638608984024
Sum of each column:
1.7988638608984024
Sum of each row:
AxisError: axis 1 is out of bounds for array of dimension 1
A = np.arange(1,10).reshape((3,3))
print(A)
[[1 2 3]
[4 5 6]
[7 8 9]]
#chess exrcise correction
a = np.zeros(64,dtype='int64').reshape(8,8)
a[1::2,1::2]=1
print(a)
[[0 0 0 0 0 0 0 0]
[0 1 0 1 0 1 0 1]
[0 0 0 0 0 0 0 0]
[0 1 0 1 0 1 0 1]
[0 0 0 0 0 0 0 0]
[0 1 0 1 0 1 0 1]
[0 0 0 0 0 0 0 0]
[0 1 0 1 0 1 0 1]]
#correction exercise 3
a=np.arange(21)
a[9:16]=-a[9:16]
print(a)
[ 0 1 2 3 4 5 6 7 8 -9 -10 -11 -12 -13 -14 -15 16 17
18 19 20]
#correction 6 identity matrix
a=np.identity(3)
print(a)
[[1. 0. 0.]
[0. 1. 0.]
[0. 0. 1.]]
#7 4*4 matrix with 0 in the middle and 1 outside
abs(np.identity(4)-1).astype(int)
#7 correction exercise with summing
a=np.arange(9).reshape(3,3)
print(a)
print(a.sum(axis=0))
print(a.sum(axis=1))
[[0 1 2]
[3 4 5]
[6 7 8]]
[ 9 12 15]
[ 3 12 21]
#correction 8
a=np.arange(1,10).reshape(3,3)
print(a)
[[1 2 3]
[4 5 6]
[7 8 9]]
a[2,0:2]
#correction 9
a=np.arange(100)
def closest(arr,scalar):
return arr[abs(arr-scalar).argmin]
abs(a-34.9).argmin()
closest(a,34.9)
NameError: name 'closest' is not defined
data=np.array([[-1.26356584, 7.16376914, 6.65286967],
[-0.79056614, 5.05922807, 5.64702233],
[ 0.9660033 , 7.83589409, 5.96605105],
[-4.0160404 , 21.32977635, 21.69702124],
[-1.90358345, 9.73677094, 8.75134229],
[ 1.41069079, 8.51979406, 7.06018639],
[-4.15750907, 23.57576646, 22.89407545],
[-0.95710097, 8.88593669, 5.94832755],
[-3.72926405, 20.08672219, 19.39756749],
[-1.36434358, 6.7754983 , 6.92703833],
[-3.7457475 , 17.27308928, 19.52512407],
[ 1.92613303, 10.87157562, 8.84074446],
[-1.56563311, 6.30979793, 7.53759814],
[ 0.76638661, 9.28079606, 5.60804912],
[ 2.8330194 , 15.00493077, 13.30886972],
[-0.2603251 , 5.89893621, 5.07015763],
[-0.67384821, 8.67347897, 5.47007485],
[-2.25400635, 11.87185912, 10.25960495],
[-0.0376848 , 2.78301217, 5.0014702 ],
[ 2.64698034, 13.66193193, 12.25344436],
[ 0.14766321, 6.53968706, 5.02257291],
[ 1.76918496, 10.38462665, 8.24033067],
[ 0.67491 , 3.99177717, 5.47155742],
[ 4.26052585, 21.89589366, 23.79183816],
[-1.75961512, 6.62245674, 8.20537042],
[-0.36331332, 3.99068072, 5.13664869],
[-2.57934635, 11.06156009, 11.88750898],
[-1.02561026, 4.22509033, 6.08894907],
[-1.02165089, 5.06891893, 6.08055753],
[ 0.91152627, 9.42137172, 5.86016393],
[ 0.58752794, 7.86272759, 5.35735503],
[-1.94426636, 9.75354974, 8.91340122],
[-1.36886087, 4.8466919 , 6.93982017],
[-0.95503157, 5.14047135, 5.94423112],
[-0.51338211, 1.71524226, 5.27285023],
[ 0.53337204, 2.8593825 , 5.29451224],
[-0.36798269, 5.16786643, 5.14018374],
[-3.32224244, 15.90474381, 16.42629667],
[ 1.19857916, 5.69001364, 6.4872237 ],
[ 1.64779036, 6.62328328, 7.81090887],
[-2.12506371, 9.54200275, 9.67505541],
[-3.94864545, 22.34174753, 21.14132316],
[-0.67638817, 5.90909652, 5.47362527],
[ 1.49796204, 6.59235796, 7.32297464],
[ 0.67307103, 5.66239422, 5.46899115],
[ 1.03725155, 5.28763312, 6.1138098 ],
[-0.69795809, 1.49385788, 5.5043146 ],
[ 0.16421034, 5.28917845, 5.0279154 ],
[ 0.3590795 , 5.76577031, 5.13348242],
[-0.59050754, 7.96916922, 5.36098882]])
x=data[:,0]
print(x)
[-1.26356584 -0.79056614 0.9660033 -4.0160404 -1.90358345 1.41069079
-4.15750907 -0.95710097 -3.72926405 -1.36434358 -3.7457475 1.92613303
-1.56563311 0.76638661 2.8330194 -0.2603251 -0.67384821 -2.25400635
-0.0376848 2.64698034 0.14766321 1.76918496 0.67491 4.26052585
-1.75961512 -0.36331332 -2.57934635 -1.02561026 -1.02165089 0.91152627
0.58752794 -1.94426636 -1.36886087 -0.95503157 -0.51338211 0.53337204
-0.36798269 -3.32224244 1.19857916 1.64779036 -2.12506371 -3.94864545
-0.67638817 1.49796204 0.67307103 1.03725155 -0.69795809 0.16421034
0.3590795 -0.59050754]
y=data[:,1]
y_pred=data[:,2]
plt.plot(x,y,"r.")
plt.show()
import matplotlib.pyplot as plt
from sklearn.metrics import r2_score as R2
from sklearn.metrics import mean_squared_error as MSE
MSE(y,y_pred)
R2(y,y_pred)
y_pred=data[:,2]
plt.plot(x,y,'r.',x,y_pred,'g.')
plt.show()
import pandas as pd
from sklearn.datasets import load_iris
ds=load_iris()
print(ds.DESCR)
.. _iris_dataset:
Iris plants dataset
--------------------
**Data Set Characteristics:**
:Number of Instances: 150 (50 in each of three classes)
:Number of Attributes: 4 numeric, predictive attributes and the class
:Attribute Information:
- sepal length in cm
- sepal width in cm
- petal length in cm
- petal width in cm
- class:
- Iris-Setosa
- Iris-Versicolour
- Iris-Virginica
:Summary Statistics:
============== ==== ==== ======= ===== ====================
Min Max Mean SD Class Correlation
============== ==== ==== ======= ===== ====================
sepal length: 4.3 7.9 5.84 0.83 0.7826
sepal width: 2.0 4.4 3.05 0.43 -0.4194
petal length: 1.0 6.9 3.76 1.76 0.9490 (high!)
petal width: 0.1 2.5 1.20 0.76 0.9565 (high!)
============== ==== ==== ======= ===== ====================
:Missing Attribute Values: None
:Class Distribution: 33.3% for each of 3 classes.
:Creator: R.A. Fisher
:Donor: Michael Marshall (MARSHALL%PLU@io.arc.nasa.gov)
:Date: July, 1988
The famous Iris database, first used by Sir R.A. Fisher. The dataset is taken
from Fisher's paper. Note that it's the same as in R, but not as in the UCI
Machine Learning Repository, which has two wrong data points.
This is perhaps the best known database to be found in the
pattern recognition literature. Fisher's paper is a classic in the field and
is referenced frequently to this day. (See Duda & Hart, for example.) The
data set contains 3 classes of 50 instances each, where each class refers to a
type of iris plant. One class is linearly separable from the other 2; the
latter are NOT linearly separable from each other.
.. topic:: References
- Fisher, R.A. "The use of multiple measurements in taxonomic problems"
Annual Eugenics, 7, Part II, 179-188 (1936); also in "Contributions to
Mathematical Statistics" (John Wiley, NY, 1950).
- Duda, R.O., & Hart, P.E. (1973) Pattern Classification and Scene Analysis.
(Q327.D83) John Wiley & Sons. ISBN 0-471-22361-1. See page 218.
- Dasarathy, B.V. (1980) "Nosing Around the Neighborhood: A New System
Structure and Classification Rule for Recognition in Partially Exposed
Environments". IEEE Transactions on Pattern Analysis and Machine
Intelligence, Vol. PAMI-2, No. 1, 67-71.
- Gates, G.W. (1972) "The Reduced Nearest Neighbor Rule". IEEE Transactions
on Information Theory, May 1972, 431-433.
- See also: 1988 MLC Proceedings, 54-64. Cheeseman et al"s AUTOCLASS II
conceptual clustering system finds 3 classes in the data.
- Many, many more ...
ds.feature_names
ds.data
df = pd.DataFrame
print(df)
<class 'pandas.core.frame.DataFrame'>
shape = df.shape
print(shape)
<property object at 0x7f8079852350>
ds.target
len(ds.target)
import numpy as np