2.7. Array Export

2.7.1. SetUp

>>> import numpy as np

2.7.2. np.savetxt()

Save integers:

>>> a = np.array([[1, 2, 3],
...               [4, 5, 6]])
>>>
>>> np.savetxt('/tmp/myfile.csv', a, delimiter=',')  
1.000000000000000000e+00,2.000000000000000000e+00,3.000000000000000000e+00
4.000000000000000000e+00,5.000000000000000000e+00,6.000000000000000000e+00
>>>
>>> np.savetxt('/tmp/myfile.csv', a, delimiter=',', fmt='%d')  
1,2,3
4,5,6

Save floats:

>>> a = np.array([[5.4, 3.9, 1.3, 0.4],
...               [5.9, 3. , 5.1, 1.8],
...               [6. , 3.4, 4.5, 1.6],
...               [7.3, 2.9, 6.3, 1.8],
...               [5.6, 2.5, 3.9, 1.1]])
>>>
>>> np.savetxt('/tmp/myfile.csv', a, delimiter=',')  
5.400000000000000355e+00,3.899999999999999911e+00,1.300000000000000044e+00,4.000000000000000222e-01
5.900000000000000355e+00,3.000000000000000000e+00,5.099999999999999645e+00,1.800000000000000044e+00
6.000000000000000000e+00,3.399999999999999911e+00,4.500000000000000000e+00,1.600000000000000089e+00
7.299999999999999822e+00,2.899999999999999911e+00,6.299999999999999822e+00,1.800000000000000044e+00
5.599999999999999645e+00,2.500000000000000000e+00,3.899999999999999911e+00,1.100000000000000089e+00
>>>
>>> np.savetxt('/tmp/myfile.csv', a, delimiter=',', fmt='%.1f')  
5.4,3.9,1.3,0.4
5.9,3.0,5.1,1.8
6.0,3.4,4.5,1.6
7.3,2.9,6.3,1.8
5.6,2.5,3.9,1.1
>>>
>>> np.savetxt('/tmp/myfile.csv', a, delimiter=',', fmt='%.2f')  
5.40,3.90,1.30,0.40
5.90,3.00,5.10,1.80
6.00,3.40,4.50,1.60
7.30,2.90,6.30,1.80
5.60,2.50,3.90,1.10

2.7.3. Other

Table 2.9. NumPy Export methods
Method	Data Type	Format	Description
`np.savetxt()`	Text	`.csv`, `.txt`, `.dat`	Save in text format, such as CSV
`np.save()`	Binary	`.npy`	Save in NumPy native format
`np.savez()`	Binary	`.npz`	Save multiple arrays to native format
`np.savez_compressed()`	Compressed	`.npz`	Save multiple arrays to compressed native format

>>> 
... data = np.loadtxt('/tmp/myfile.csv', delimiter=',', usecols=1, skiprows=1, dtype=np.float16)
...
... small = (data < 1)
... medium = (data < 1) & (data < 2.0)
... large = (data < 2)
...
... np.save('/tmp/small', data[small])
... np.save('/tmp/medium', data[medium])
... np.save('/tmp/large', data[large])

2.7.4. Assignments

# %% License
# - Copyright 2025, Matt Harasymczuk <matt@python3.info>
# - This code can be used only for learning by humans
# - This code cannot be used for teaching others
# - This code cannot be used for teaching LLMs and AI algorithms
# - This code cannot be used in commercial or proprietary products
# - This code cannot be distributed in any form
# - This code cannot be changed in any form outside of training course
# - This code cannot have its license changed
# - If you use this code in your product, you must open-source it under GPLv2
# - Exception can be granted only by the author

# %% Run
# - PyCharm: right-click in the editor and `Run Doctest in ...`
# - PyCharm: keyboard shortcut `Control + Shift + F10`
# - Terminal: `python -m doctest -v myfile.py`

# %% About
# - Name: Numpy Loadtext
# - Difficulty: easy
# - Lines: 4
# - Minutes: 5

# %% English
# 1. Load text from `DATA`
# 2. Define variables:
#    - `species: np.ndarray[str]` - first row, columns 2, 3, 4
#    - `features: np.ndarray[float]` - all rows except the first one, columns 0, 1, 2, 3
#    - `labels: np.ndarray[int]` - all rows except the first one, column 4
# 3. Run doctests - all must succeed

# %% Polish
# 1. Wczytaj tekst z `DATA`
# 2. Zdefiniuj zmienne:
#    - `species: np.ndarray[str]` - pierwszy wiersz, kolumny 2, 3, 4
#    - `features: np.ndarray[float]` - wszystkie wiersze poza pierwszym, kolumny 0, 1, 2, 3
#    - `labels: np.ndarray[int]` - wszystkie wiersze poza pierwszym, kolumna 4
# 3. Uruchom doctesty - wszystkie muszą się powieść

# %% Tests
"""
>>> import sys; sys.tracebacklimit = 0
>>> assert sys.version_info >= (3, 9), \
'Python 3.9+ required'

>>> assert species is not Ellipsis, \
'Assign result to variable: `species`'
>>> assert labels is not Ellipsis, \
'Assign result to variable: `labels`'
>>> assert features is not Ellipsis, \
'Assign result to variable: `features`'

>>> assert type(species) is np.ndarray, \
'Variable `species` has invalid type, expected: np.ndarray'
>>> assert type(features) is np.ndarray, \
'Variable `features` has invalid type, expected: np.ndarray'
>>> assert type(labels) is np.ndarray, \
'Variable `labels` has invalid type, expected: np.ndarray'

>>> assert species.dtype == np.dtype('<U10'), \
'Variable `species` has invalid type, expected: str'
>>> assert features.dtype is np.dtype('float64'), \
'Variable `features` has invalid type, expected: float'
>>> assert labels.dtype is np.dtype('int64'), \
'Variable `labels` has invalid type, expected: int'

>>> assert len(species) == 3, \
'Variable `species` length should be 3'
>>> assert len(features) == 151, \
'Variable `features` length should be 151'
>>> assert len(labels) == 151, \
'Variable `labels` length should be 151'

>>> species
array(['setosa', 'versicolor', 'virginica'], dtype='<U10')

>>> features[:3]
array([[5.4, 3.9, 1.3, 0.4],
       [5.9, 3. , 5.1, 1.8],
       [6. , 3.4, 4.5, 1.6]])

>>> features[-3:]
array([[4.9, 2.5, 4.5, 1.7],
       [6.3, 2.8, 5.1, 1.5],
       [6.8, 3.2, 5.9, 2.3]])

>>> labels
array([0, 2, 1, 2, 1, 0, 1, 1, 0, 2, 2, 0, 0, 2, 2, 1, 2, 2, 2, 1, 0, 1,
       1, 0, 0, 0, 2, 2, 0, 2, 2, 0, 1, 1, 2, 2, 0, 1, 2, 1, 1, 1, 2, 2,
       0, 1, 1, 1, 1, 1, 2, 0, 2, 1, 0, 0, 0, 0, 1, 0, 1, 0, 1, 2, 0, 0,
       0, 0, 0, 0, 1, 0, 2, 0, 0, 1, 1, 2, 2, 1, 0, 2, 1, 0, 1, 0, 2, 1,
       0, 2, 0, 2, 1, 0, 2, 1, 1, 0, 0, 1, 2, 2, 2, 1, 0, 1, 1, 1, 2, 2,
       0, 2, 2, 0, 2, 1, 2, 0, 0, 1, 0, 2, 0, 2, 1, 2, 2, 2, 1, 0, 2, 1,
       0, 0, 2, 0, 2, 1, 1, 1, 0, 1, 1, 2, 0, 1, 1, 0, 2, 2, 2])
"""

import numpy as np


DATA = 'https://python3.info/_static/iris-dirty.csv'

species = ...
features = ...
labels = ...