CoCalc -- 2017-04-07-142242.ipynb

Jupyter notebook 2017-04-07-142242.ipynb

Project: pyton

Path: 2017-04-07-142242.ipynb

Views: ¹⁰⁸

Kernel: Python 3 (Ubuntu Linux)

In [1]:

import numpy as np

In [2]:

a=np.array([1,2,3,4,5])
print(a)

[1 2 3 4 5]

In [3]:

print(len(a))
print(a.size)

5
5

In [4]:

a.dtype

dtype('int64')

In [5]:

a.shape

(5,)

In [6]:

a1=np.array([1.,2.,3.,4.,5.])
print(a1,a1.dtype,a1.shape)

[ 1.  2.  3.  4.  5.] float64 (5,)

In [7]:

a2=np.array(([1,2,3,4,5]), dtype=np.float16)
print(a2,a2.dtype,a2.shape)

[ 1.  2.  3.  4.  5.] float16 (5,)

In [8]:

a2.astype(np.int32)

array([1, 2, 3, 4, 5], dtype=int32)

In [9]:

A=np.array([[1.,2.],[3.,4.],[5.,6.]])
print(A)

[[ 1.  2.]
 [ 3.  4.]
 [ 5.  6.]]

In [10]:

print('len: ', len(A))
print('size: ', A.size)
print('dtype: ', A.dtype)
print('shape: ', A.shape)

len:  3
size:  6
dtype:  float64
shape:  (3, 2)

In [11]:

AT=A.T
print(AT)
print('len: ', len(AT))
print('size: ', AT.size)
print('dtype: ', AT.dtype)
print('shape: ', AT.shape)

[[ 1.  3.  5.]
 [ 2.  4.  6.]]
len:  2
size:  6
dtype:  float64
shape:  (2, 3)

In [12]:

at=a.T
print(at)
print('len: ', len(at))
print('size: ', at.size)
print('dtype: ', at.dtype)
print('shape: ', at.shape)

[1 2 3 4 5]
len:  5
size:  5
dtype:  int64
shape:  (5,)

In [13]:

aa=A.reshape((6,))
print(A)
print(aa)

[[ 1.  2.]
 [ 3.  4.]
 [ 5.  6.]]
[ 1.  2.  3.  4.  5.  6.]

In [14]:

ab=A.reshape((6,1))
print(A)
print(ab)

[[ 1.  2.]
 [ 3.  4.]
 [ 5.  6.]]
[[ 1.]
 [ 2.]
 [ 3.]
 [ 4.]
 [ 5.]
 [ 6.]]

In [15]:

ab=A.reshape((1,6))
print(A)
print(ab)

[[ 1.  2.]
 [ 3.  4.]
 [ 5.  6.]]
[[ 1.  2.  3.  4.  5.  6.]]

In [16]:

ac=A.reshape((1,-1))
print(A)
print(ac)

[[ 1.  2.]
 [ 3.  4.]
 [ 5.  6.]]
[[ 1.  2.  3.  4.  5.  6.]]

In [17]:

A[1,1]

4.0

In [18]:

A[1,:]

array([ 3.,  4.])

In [19]:

A[:,1]

array([ 2.,  4.,  6.])

In [20]:

A.max()

6.0

In [21]:

A.max(axis=0)

array([ 5.,  6.])

In [22]:

A.max(axis=1)

array([ 2.,  4.,  6.])

In [23]:

B=np.random.random(7)
print(B)
B.sort()
print(B)

[ 0.5647215   0.00094002  0.24878213  0.68678843  0.52699816  0.03735719
  0.2454302 ]
[ 0.00094002  0.03735719  0.2454302   0.24878213  0.52699816  0.5647215
  0.68678843]

In [24]:

B2=np.random.random(size=(2,3))
print(B2)
B2.sort()
print(B2)

[[ 0.64321401  0.65931002  0.21608559]
 [ 0.92885038  0.564786    0.39182436]]
[[ 0.21608559  0.64321401  0.65931002]
 [ 0.39182436  0.564786    0.92885038]]

In [25]:

B3=np.random.random(size=(2,3))
print(B3)
B3.sort(axis=0)
print(B3)

[[ 0.16288666  0.11172614  0.35282611]
 [ 0.38132885  0.02666066  0.15043217]]
[[ 0.16288666  0.02666066  0.15043217]
 [ 0.38132885  0.11172614  0.35282611]]

In [26]:

B4=np.random.random(size=(2,3))
print(B4)
B4.sort(axis=1)
print(B4)

[[ 0.12819814  0.48234593  0.86324019]
 [ 0.45798466  0.12867528  0.55265798]]
[[ 0.12819814  0.48234593  0.86324019]
 [ 0.12867528  0.45798466  0.55265798]]

In [27]:

B5=np.random.random(size=(2,3))
print(B5)
print(B5.argsort())

[[ 0.30914498  0.64406892  0.08580514]
 [ 0.25394587  0.39194642  0.92343702]]
[[2 0 1]
 [0 1 2]]

In [28]:

A1=np.array([1.,2.,3.])
A2=np.array([3.,2.,1.])
np.inner(A1, A2)

10.0

In [29]:

M1=np.array([[2.,3.],[3.,1.],[1.,2]])
print(M1)

[[ 2.  3.]
 [ 3.  1.]
 [ 1.  2.]]

In [30]:

X1=np.array([1.,1.,1.])
X2=np.array([1.,1.])
np.dot(M1,X2)

array([ 5.,  4.,  3.])

In [31]:

RA=np.array([(1,2.),(2,3.)], dtype=[('id', np.int32),('val', np.float64)])
print(RA)
print(RA.dtype)

[(1,  2.) (2,  3.)]
[('id', '<i4'), ('val', '<f8')]

In [32]:

RA[0]

(1,  2.)

In [33]:

print(RA['id'],RA['val'])

[1 2] [ 2.  3.]

In [34]:

RA[0]['id']

1

In [35]:

print(RA.tostring())

b'\x01\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00@\x02\x00\x00\x00\x00\x00\x00\x00\x00\x00\x08@'

In [36]:

print(M1.tostring())

b'\x00\x00\x00\x00\x00\x00\x00@\x00\x00\x00\x00\x00\x00\x08@\x00\x00\x00\x00\x00\x00\x08@\x00\x00\x00\x00\x00\x00\xf0?\x00\x00\x00\x00\x00\x00\xf0?\x00\x00\x00\x00\x00\x00\x00@'

In [37]:

np.fromstring(RA.tostring(), dtype=[('id',np.int32),('val',np.float64)])

array([(1,  2.), (2,  3.)], 
      dtype=[('id', '<i4'), ('val', '<f8')])

In [38]:

M1.tolist()

[[2.0, 3.0], [3.0, 1.0], [1.0, 2.0]]

In [39]:

RA.tolist()

[(1, 2.0), (2, 3.0)]

In [40]:

X1=np.random.random(7)
X2=np.random.random(7)
print(X1)
print(X2)
print(X1+X2)

[ 0.63959344  0.72079659  0.86719556  0.24628904  0.15319488  0.05360769
  0.97353974]
[ 0.48495132  0.68221772  0.09359279  0.29566355  0.18079382  0.52736749
  0.78261675]
[ 1.12454475  1.4030143   0.96078836  0.54195259  0.3339887   0.58097517
  1.75615649]

In [41]:

print(X1**2+X2**2)

[ 0.64425754  0.98496873  0.76078776  0.14807523  0.05615508  0.28099025
  1.5602686 ]

In [42]:

print(np.sqrt(X1))

[ 0.79974586  0.8489974   0.93123336  0.49627516  0.39140117  0.23153334
  0.98668118]

In [43]:

print(np.exp(X1))

[ 1.89571     2.0560704   2.38022629  1.27926927  1.16555209  1.0550706
  2.64729865]

In [44]:

text="""\
1 2.0
2 3.0
"""

In [45]:

import io

In [46]:

f=io.StringIO(text)
AA=np.loadtxt(f,delimiter=' ',dtype=[('id',np.int32), ('val', np.float64)])
f.close()
print(AA)

[(1,  2.) (2,  3.)]

In [47]:

print(type(AA), AA.dtype,AA.shape)

<class 'numpy.ndarray'> [('id', '<i4'), ('val', '<f8')] (2,)

In [48]:

#f2=io.StringIO("")
#np.savetxt(f2,AA,delimiter=',', fmt=[('id','%i'), ('val','%.if')])
#2.close()

In [49]:

#np.savetxt?

In [50]:

import pandas as pd

In [51]:

# sepal -чашелистник
# petal - лепесток
attr_names = """sepal lenght
sepal width
petal length
petal width
class"""
attr_names = attr_names.split("\n")
print(attr_names)

['sepal lenght', 'sepal width', 'petal length', 'petal width', 'class']

In [52]:

iris_df=pd.read_csv("data/iris.data", sep=',', names=attr_names)

In [53]:

print(type(iris_df))
iris_df

<class 'pandas.core.frame.DataFrame'>

	sepal lenght	sepal width	petal length	petal width	class
0	5.1	3.5	1.4	0.2	Iris-setosa
1	4.9	3.0	1.4	0.2	Iris-setosa
2	4.7	3.2	1.3	0.2	Iris-setosa
3	4.6	3.1	1.5	0.2	Iris-setosa
4	5.0	3.6	1.4	0.2	Iris-setosa
5	5.4	3.9	1.7	0.4	Iris-setosa
6	4.6	3.4	1.4	0.3	Iris-setosa
7	5.0	3.4	1.5	0.2	Iris-setosa
8	4.4	2.9	1.4	0.2	Iris-setosa
9	4.9	3.1	1.5	0.1	Iris-setosa
10	5.4	3.7	1.5	0.2	Iris-setosa
11	4.8	3.4	1.6	0.2	Iris-setosa
12	4.8	3.0	1.4	0.1	Iris-setosa
13	4.3	3.0	1.1	0.1	Iris-setosa
14	5.8	4.0	1.2	0.2	Iris-setosa
15	5.7	4.4	1.5	0.4	Iris-setosa
16	5.4	3.9	1.3	0.4	Iris-setosa
17	5.1	3.5	1.4	0.3	Iris-setosa
18	5.7	3.8	1.7	0.3	Iris-setosa
19	5.1	3.8	1.5	0.3	Iris-setosa
20	5.4	3.4	1.7	0.2	Iris-setosa
21	5.1	3.7	1.5	0.4	Iris-setosa
22	4.6	3.6	1.0	0.2	Iris-setosa
23	5.1	3.3	1.7	0.5	Iris-setosa
24	4.8	3.4	1.9	0.2	Iris-setosa
25	5.0	3.0	1.6	0.2	Iris-setosa
26	5.0	3.4	1.6	0.4	Iris-setosa
27	5.2	3.5	1.5	0.2	Iris-setosa
28	5.2	3.4	1.4	0.2	Iris-setosa
29	4.7	3.2	1.6	0.2	Iris-setosa
...	...	...	...	...	...
120	6.9	3.2	5.7	2.3	Iris-virginica
121	5.6	2.8	4.9	2.0	Iris-virginica
122	7.7	2.8	6.7	2.0	Iris-virginica
123	6.3	2.7	4.9	1.8	Iris-virginica
124	6.7	3.3	5.7	2.1	Iris-virginica
125	7.2	3.2	6.0	1.8	Iris-virginica
126	6.2	2.8	4.8	1.8	Iris-virginica
127	6.1	3.0	4.9	1.8	Iris-virginica
128	6.4	2.8	5.6	2.1	Iris-virginica
129	7.2	3.0	5.8	1.6	Iris-virginica
130	7.4	2.8	6.1	1.9	Iris-virginica
131	7.9	3.8	6.4	2.0	Iris-virginica
132	6.4	2.8	5.6	2.2	Iris-virginica
133	6.3	2.8	5.1	1.5	Iris-virginica
134	6.1	2.6	5.6	1.4	Iris-virginica
135	7.7	3.0	6.1	2.3	Iris-virginica
136	6.3	3.4	5.6	2.4	Iris-virginica
137	6.4	3.1	5.5	1.8	Iris-virginica
138	6.0	3.0	4.8	1.8	Iris-virginica
139	6.9	3.1	5.4	2.1	Iris-virginica
140	6.7	3.1	5.6	2.4	Iris-virginica
141	6.9	3.1	5.1	2.3	Iris-virginica
142	5.8	2.7	5.1	1.9	Iris-virginica
143	6.8	3.2	5.9	2.3	Iris-virginica
144	6.7	3.3	5.7	2.5	Iris-virginica
145	6.7	3.0	5.2	2.3	Iris-virginica
146	6.3	2.5	5.0	1.9	Iris-virginica
147	6.5	3.0	5.2	2.0	Iris-virginica
148	6.2	3.4	5.4	2.3	Iris-virginica
149	5.9	3.0	5.1	1.8	Iris-virginica

150 rows × 5 columns

In [54]:

iris_df.index

RangeIndex(start=0, stop=150, step=1)

In [58]:

col = iris_df ["sepal length"]
print(type(col))
col

---------------------------------------------------------------------------
KeyError                                  Traceback (most recent call last)
/usr/local/lib/python3.4/dist-packages/pandas/indexes/base.py in get_loc(self, key, method, tolerance)
   2133             try:
-> 2134                 return self._engine.get_loc(key)
   2135             except KeyError:
pandas/index.pyx in pandas.index.IndexEngine.get_loc (pandas/index.c:4433)()
pandas/index.pyx in pandas.index.IndexEngine.get_loc (pandas/index.c:4279)()
pandas/src/hashtable_class_helper.pxi in pandas.hashtable.PyObjectHashTable.get_item (pandas/hashtable.c:13742)()
pandas/src/hashtable_class_helper.pxi in pandas.hashtable.PyObjectHashTable.get_item (pandas/hashtable.c:13696)()
KeyError: 'sepal length'

During handling of the above exception, another exception occurred:
KeyError                                  Traceback (most recent call last)
<ipython-input-58-2ca01e06736b> in <module>()
----> 1 col = iris_df ["sepal length"]
      2 print(type(col))
      3 col
/usr/local/lib/python3.4/dist-packages/pandas/core/frame.py in __getitem__(self, key)
   2057             return self._getitem_multilevel(key)
   2058         else:
-> 2059             return self._getitem_column(key)
   2060 
   2061     def _getitem_column(self, key):
/usr/local/lib/python3.4/dist-packages/pandas/core/frame.py in _getitem_column(self, key)
   2064         # get column
   2065         if self.columns.is_unique:
-> 2066             return self._get_item_cache(key)
   2067 
   2068         # duplicate columns & possible reduce dimensionality
/usr/local/lib/python3.4/dist-packages/pandas/core/generic.py in _get_item_cache(self, item)
   1384         res = cache.get(item)
   1385         if res is None:
-> 1386             values = self._data.get(item)
   1387             res = self._box_item_values(item, values)
   1388             cache[item] = res
/usr/local/lib/python3.4/dist-packages/pandas/core/internals.py in get(self, item, fastpath)
   3541 
   3542             if not isnull(item):
-> 3543                 loc = self.items.get_loc(item)
   3544             else:
   3545                 indexer = np.arange(len(self.items))[isnull(self.items)]
/usr/local/lib/python3.4/dist-packages/pandas/indexes/base.py in get_loc(self, key, method, tolerance)
   2134                 return self._engine.get_loc(key)
   2135             except KeyError:
-> 2136                 return self._engine.get_loc(self._maybe_cast_indexer(key))
   2137 
   2138         indexer = self.get_indexer([key], method=method, tolerance=tolerance)
pandas/index.pyx in pandas.index.IndexEngine.get_loc (pandas/index.c:4433)()
pandas/index.pyx in pandas.index.IndexEngine.get_loc (pandas/index.c:4279)()
pandas/src/hashtable_class_helper.pxi in pandas.hashtable.PyObjectHashTable.get_item (pandas/hashtable.c:13742)()
pandas/src/hashtable_class_helper.pxi in pandas.hashtable.PyObjectHashTable.get_item (pandas/hashtable.c:13696)()
KeyError: 'sepal length'

In [ ]:

iris_df[attr_names[0]]

In [ ]:

class_num = iris_df["class"]
class_names = class_num.unique()
class_names = list(class_names)
print(class_names)
class_num = class_num.apply(lambda val: class_names.index(val)+1)
print(class_num)

In [ ]:

iris_df["class_num"] = class_num
iris_df

In [ ]:

X1 = iris_df[attr_names[0]].values
X2 = iris_df[attr_names[1]].values
X3 = iris_df[attr_names[2]].values
X4 = iris_df[attr_names[3]].values
print(X4)

In [ ]:

X = np.c_[X1, X2, X3, X4]
print(X.shape)
print(X)

In [ ]:

Y = iris_df["class_num"].values
print(Y)

In [ ]:

import matplotlib.pyplot as plt

In [ ]:

X[Y==1]

In [ ]:

fltr = Y==1
print(fltr)
print(X[fltr])

In [ ]:

plt.figure(figsize=(5,4))
idx1 = (Y==1)
idx2 = (Y==2)
idx3 = (Y==3)
plt.scatter(X[:,1][idx1], X[:,2][idx1], s=36, c='r', label='класс 1')
plt.scatter(X[:,1][idx2], X[:,2][idx2], s=36, c='b', label='класс 2')
plt.scatter(X[:,1][idx3], X[:,2][idx3], s=36, c='g', label='класс 3')
plt.xlabel(attr_names[1])
plt.ylabel(attr_names[2])
plt.legend(loc='best')
plt.grid(1)
plt.show()

In [ ]:

m=4
idx=(Y==1)

In [ ]: