Interactive online version:
Import the LArray library:
[1]:
from larray import *
[2]:
# load 'demography_eurostat' dataset
demography_eurostat = load_example_data('demography_eurostat')
# extract the 'population' array from the dataset
population = demography_eurostat.population
population
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
Cell In[2], line 2
1 # load 'demography_eurostat' dataset
----> 2 demography_eurostat = load_example_data('demography_eurostat')
4 # extract the 'population' array from the dataset
5 population = demography_eurostat.population
File ~/checkouts/readthedocs.org/user_builds/larray/envs/0.34.3/lib/python3.11/site-packages/larray/example.py:97, in load_example_data(name)
95 available_datasets = list(AVAILABLE_EXAMPLE_DATA.keys())
96 raise ValueError(f"example_data must be chosen from list {available_datasets}")
---> 97 return la.Session(AVAILABLE_EXAMPLE_DATA[name])
File ~/checkouts/readthedocs.org/user_builds/larray/envs/0.34.3/lib/python3.11/site-packages/larray/core/session.py:98, in Session.__init__(self, meta, *args, **kwargs)
94 elements = {a.name: a for a in args}
96 if isinstance(elements, (str, Path)):
97 # assume elements is a filename
---> 98 self.load(elements)
99 self.update(**kwargs)
100 else:
101 # iterable of tuple or dict-like
File ~/checkouts/readthedocs.org/user_builds/larray/envs/0.34.3/lib/python3.11/site-packages/larray/core/session.py:438, in Session.load(self, fname, names, engine, display, **kwargs)
436 else:
437 handler = handler_cls(fname)
--> 438 metadata, objects = handler.read(names, display=display, **kwargs)
439 self._update_from_iterable(objects.items())
440 self.meta = metadata
File ~/checkouts/readthedocs.org/user_builds/larray/envs/0.34.3/lib/python3.11/site-packages/larray/inout/common.py:139, in FileHandler.read(self, keys, display, ignore_exceptions, *args, **kwargs)
114 def read(self, keys, *args, display=False, ignore_exceptions=False, **kwargs) -> Tuple[Metadata, dict]:
115 r"""
116 Read file content (HDF, Excel, CSV, ...) and returns a dictionary containing loaded objects.
117
(...)
137 Dictionary containing the loaded objects.
138 """
--> 139 self._open_for_read()
140 metadata = self._read_metadata()
141 item_types = self.item_types()
File ~/checkouts/readthedocs.org/user_builds/larray/envs/0.34.3/lib/python3.11/site-packages/larray/inout/hdf.py:138, in PandasHDFHandler._open_for_read(self)
137 def _open_for_read(self):
--> 138 self.handle = HDFStore(self.fname, mode='r')
File ~/checkouts/readthedocs.org/user_builds/larray/envs/0.34.3/lib/python3.11/site-packages/pandas/io/pytables.py:566, in HDFStore.__init__(self, path, mode, complevel, complib, fletcher32, **kwargs)
563 if "format" in kwargs:
564 raise ValueError("format is not a defined argument for HDFStore")
--> 566 tables = import_optional_dependency("tables")
568 if complib is not None and complib not in tables.filters.all_complibs:
569 raise ValueError(
570 f"complib only supports {tables.filters.all_complibs} compression."
571 )
File ~/checkouts/readthedocs.org/user_builds/larray/envs/0.34.3/lib/python3.11/site-packages/pandas/compat/_optional.py:135, in import_optional_dependency(name, extra, errors, min_version)
130 msg = (
131 f"Missing optional dependency '{install_name}'. {extra} "
132 f"Use pip or conda to install {install_name}."
133 )
134 try:
--> 135 module = importlib.import_module(name)
136 except ImportError:
137 if errors == "raise":
File ~/.asdf/installs/python/3.11.9/lib/python3.11/importlib/__init__.py:126, in import_module(name, package)
124 break
125 level += 1
--> 126 return _bootstrap._gcd_import(name[level:], package, level)
File <frozen importlib._bootstrap>:1204, in _gcd_import(name, package, level)
File <frozen importlib._bootstrap>:1176, in _find_and_load(name, import_)
File <frozen importlib._bootstrap>:1147, in _find_and_load_unlocked(name, import_)
File <frozen importlib._bootstrap>:690, in _load_unlocked(spec)
File <frozen importlib._bootstrap_external>:940, in exec_module(self, module)
File <frozen importlib._bootstrap>:241, in _call_with_frames_removed(f, *args, **kwds)
File ~/checkouts/readthedocs.org/user_builds/larray/envs/0.34.3/lib/python3.11/site-packages/tables/__init__.py:44
40 raise RuntimeError("Blosc2 library not found. "
41 f"I looked for \"{', '.join(blosc2_search_paths)}\"")
43 # Necessary imports to get versions stored on the cython extension
---> 44 from .utilsextension import get_hdf5_version as _get_hdf5_version
46 from ._version import __version__
48 hdf5_version = _get_hdf5_version()
File ~/checkouts/readthedocs.org/user_builds/larray/envs/0.34.3/lib/python3.11/site-packages/tables/utilsextension.pyx:1, in init tables.utilsextension()
ValueError: numpy.dtype size changed, may indicate binary incompatibility. Expected 96 from C header, got 88 from PyObject
Inspecting Array objects
Get array summary : metadata + dimensions + description of axes + dtype + size in memory
[3]:
# Array summary: metadata + dimensions + description of axes
population.info
---------------------------------------------------------------------------
NameError Traceback (most recent call last)
Cell In[3], line 2
1 # Array summary: metadata + dimensions + description of axes
----> 2 population.info
NameError: name 'population' is not defined
Get axes
[4]:
population.axes
---------------------------------------------------------------------------
NameError Traceback (most recent call last)
Cell In[4], line 1
----> 1 population.axes
NameError: name 'population' is not defined
Get axis names
[5]:
population.axes.names
---------------------------------------------------------------------------
NameError Traceback (most recent call last)
Cell In[5], line 1
----> 1 population.axes.names
NameError: name 'population' is not defined
Get number of dimensions
[6]:
population.ndim
---------------------------------------------------------------------------
NameError Traceback (most recent call last)
Cell In[6], line 1
----> 1 population.ndim
NameError: name 'population' is not defined
Get length of each dimension
[7]:
population.shape
---------------------------------------------------------------------------
NameError Traceback (most recent call last)
Cell In[7], line 1
----> 1 population.shape
NameError: name 'population' is not defined
Get total number of elements of the array
[8]:
population.size
---------------------------------------------------------------------------
NameError Traceback (most recent call last)
Cell In[8], line 1
----> 1 population.size
NameError: name 'population' is not defined
Get type of internal data (int, float, …)
[9]:
population.dtype
---------------------------------------------------------------------------
NameError Traceback (most recent call last)
Cell In[9], line 1
----> 1 population.dtype
NameError: name 'population' is not defined
Get size in memory
[10]:
population.memory_used
---------------------------------------------------------------------------
NameError Traceback (most recent call last)
Cell In[10], line 1
----> 1 population.memory_used
NameError: name 'population' is not defined
Some Useful Functions
with total
Add totals to one or several axes:
[11]:
population.with_total('gender', label='Total')
---------------------------------------------------------------------------
NameError Traceback (most recent call last)
Cell In[11], line 1
----> 1 population.with_total('gender', label='Total')
NameError: name 'population' is not defined
See with_total for more details and examples.
where
The where function can be used to apply some computation depending on a condition:
[12]:
# where(condition, value if true, value if false)
where(population < population.mean('time'), -population, population)
---------------------------------------------------------------------------
NameError Traceback (most recent call last)
Cell In[12], line 2
1 # where(condition, value if true, value if false)
----> 2 where(population < population.mean('time'), -population, population)
NameError: name 'population' is not defined
See where for more details and examples.
clip
Set all data between a certain range:
[13]:
# values below 10 millions are set to 10 millions
population.clip(minval=10**7)
---------------------------------------------------------------------------
NameError Traceback (most recent call last)
Cell In[13], line 2
1 # values below 10 millions are set to 10 millions
----> 2 population.clip(minval=10**7)
NameError: name 'population' is not defined
[14]:
# values above 40 millions are set to 40 millions
population.clip(maxval=4*10**7)
---------------------------------------------------------------------------
NameError Traceback (most recent call last)
Cell In[14], line 2
1 # values above 40 millions are set to 40 millions
----> 2 population.clip(maxval=4*10**7)
NameError: name 'population' is not defined
[15]:
# values below 10 millions are set to 10 millions and
# values above 40 millions are set to 40 millions
population.clip(10**7, 4*10**7)
---------------------------------------------------------------------------
NameError Traceback (most recent call last)
Cell In[15], line 3
1 # values below 10 millions are set to 10 millions and
2 # values above 40 millions are set to 40 millions
----> 3 population.clip(10**7, 4*10**7)
NameError: name 'population' is not defined
[16]:
# Using vectors to define the lower and upper bounds
lower_bound = sequence(population.time, initial=5_500_000, inc=50_000)
upper_bound = sequence(population.time, 41_000_000, inc=100_000)
print(lower_bound, '\n')
print(upper_bound, '\n')
population.clip(lower_bound, upper_bound)
---------------------------------------------------------------------------
NameError Traceback (most recent call last)
Cell In[16], line 2
1 # Using vectors to define the lower and upper bounds
----> 2 lower_bound = sequence(population.time, initial=5_500_000, inc=50_000)
3 upper_bound = sequence(population.time, 41_000_000, inc=100_000)
5 print(lower_bound, '\n')
NameError: name 'population' is not defined
See clip for more details and examples.
divnot0
Replace division by 0 by 0:
[17]:
divisor = ones(population.axes, dtype=int)
divisor['Male'] = 0
divisor
---------------------------------------------------------------------------
NameError Traceback (most recent call last)
Cell In[17], line 1
----> 1 divisor = ones(population.axes, dtype=int)
2 divisor['Male'] = 0
3 divisor
NameError: name 'population' is not defined
[18]:
population / divisor
---------------------------------------------------------------------------
NameError Traceback (most recent call last)
Cell In[18], line 1
----> 1 population / divisor
NameError: name 'population' is not defined
[19]:
# we use astype(int) since the divnot0 method
# returns a float array in this case while
# we want an integer array
population.divnot0(divisor).astype(int)
---------------------------------------------------------------------------
NameError Traceback (most recent call last)
Cell In[19], line 4
1 # we use astype(int) since the divnot0 method
2 # returns a float array in this case while
3 # we want an integer array
----> 4 population.divnot0(divisor).astype(int)
NameError: name 'population' is not defined
See divnot0 for more details and examples.
ratio
The ratio (rationot0) method returns an array with all values divided by the sum of values along given axes:
[20]:
population.ratio('gender')
# which is equivalent to
population / population.sum('gender')
---------------------------------------------------------------------------
NameError Traceback (most recent call last)
Cell In[20], line 1
----> 1 population.ratio('gender')
3 # which is equivalent to
4 population / population.sum('gender')
NameError: name 'population' is not defined
percents
[21]:
# or, if you want the previous ratios in percents
population.percent('gender')
---------------------------------------------------------------------------
NameError Traceback (most recent call last)
Cell In[21], line 2
1 # or, if you want the previous ratios in percents
----> 2 population.percent('gender')
NameError: name 'population' is not defined
See percent for more details and examples.
diff
The diff method calculates the n-th order discrete difference along a given axis.
The first order difference is given by out[n+1] = in[n+1] - in[n] along the given axis.
[22]:
# calculates 'diff[year+1] = population[year+1] - population[year]'
population.diff('time')
---------------------------------------------------------------------------
NameError Traceback (most recent call last)
Cell In[22], line 2
1 # calculates 'diff[year+1] = population[year+1] - population[year]'
----> 2 population.diff('time')
NameError: name 'population' is not defined
[23]:
# calculates 'diff[year+2] = population[year+2] - population[year]'
population.diff('time', d=2)
---------------------------------------------------------------------------
NameError Traceback (most recent call last)
Cell In[23], line 2
1 # calculates 'diff[year+2] = population[year+2] - population[year]'
----> 2 population.diff('time', d=2)
NameError: name 'population' is not defined
[24]:
# calculates 'diff[year] = population[year+1] - population[year]'
population.diff('time', label='lower')
---------------------------------------------------------------------------
NameError Traceback (most recent call last)
Cell In[24], line 2
1 # calculates 'diff[year] = population[year+1] - population[year]'
----> 2 population.diff('time', label='lower')
NameError: name 'population' is not defined
See diff for more details and examples.
growth_rate
The growth_rate method calculates the growth along a given axis.
It is roughly equivalent to a.diff(axis, d, label) / a[axis.i[:-d]]:
[25]:
population.growth_rate('time')
---------------------------------------------------------------------------
NameError Traceback (most recent call last)
Cell In[25], line 1
----> 1 population.growth_rate('time')
NameError: name 'population' is not defined
See growth_rate for more details and examples.
shift
The shift method drops first label of an axis and shifts all subsequent labels
[26]:
population.shift('time')
---------------------------------------------------------------------------
NameError Traceback (most recent call last)
Cell In[26], line 1
----> 1 population.shift('time')
NameError: name 'population' is not defined
[27]:
# when shift is applied on an (increasing) time axis,
# it effectively brings "past" data into the future
population_shifted = population.shift('time')
stack({'population_shifted_2014': population_shifted[2014], 'population_2013': population[2013]}, 'array')
---------------------------------------------------------------------------
NameError Traceback (most recent call last)
Cell In[27], line 3
1 # when shift is applied on an (increasing) time axis,
2 # it effectively brings "past" data into the future
----> 3 population_shifted = population.shift('time')
4 stack({'population_shifted_2014': population_shifted[2014], 'population_2013': population[2013]}, 'array')
NameError: name 'population' is not defined
See shift for more details and examples.
Other interesting functions
There are a lot more interesting functions that you can find in the API reference in sections Aggregation Functions, Miscellaneous and Utility Functions.