hawc_hal.maptree.map_tree.MapTree.write() - Code Metrics - Inspection of "Merge pull request #4 from ColasRi/hawc_response_f..." - giacomov/hawc_hal - Measure and Improve Code Quality continuously with Scrutinizer

Passed

Push — master ( 20ef60...3972dc )

by Giacomo

created 2018-07-12 23:47 UTC

hawc_hal.maptree.map_tree.MapTree.write() B

↳ Parent: hawc_hal.maptree.map_tree

Complexity

Conditions

Size

Total Lines	50
Code Lines	20

Duplication

Lines	0
Ratio	0 %

Importance

Changes

Metric	Value
eloc	20
dl	0
loc	50
rs	8.9332
c	0
b	0
f	0
cc	5
nop	2

import os
class SomeClass:
    def some_method(self):
        """Do x and return foo."""
import numpy as np

import pandas as pd


from threeML.io.rich_display import display

from threeML.io.file_utils import sanitize_filename


from ..serialize import Serialization
from from_root_file import from_root_file

from from_hdf5_file import from_hdf5_file


import astropy.units as u



def map_tree_factory(map_tree_file, roi):
class SomeClass:
    def some_method(self):
        """Do x and return foo."""

    # Sanitize files in input (expand variables and so on)
    map_tree_file = sanitize_filename(map_tree_file)

    if os.path.splitext(map_tree_file)[-1] == '.root':


        return MapTree.from_root_file(map_tree_file, roi)

    else:

        return MapTree.from_hdf5(map_tree_file, roi)


class MapTree(object):
class SomeClass:
    def some_method(self):
        """Do x and return foo."""

    def __init__(self, analysis_bins, roi):

        self._analysis_bins = analysis_bins
        self._roi = roi

    @classmethod
    def from_hdf5(cls, map_tree_file, roi):
class SomeClass:
    def some_method(self):
        """Do x and return foo."""

        data_analysis_bins = from_hdf5_file(map_tree_file, roi)

        return cls(data_analysis_bins, roi)

    @classmethod
    def from_root_file(cls, map_tree_file, roi):
        """
        Create a MapTree object from a ROOT file and a ROI. Do not use this directly, use map_tree_factory instead.

        :param map_tree_file:
        :param roi:
        :return:
        """

        data_analysis_bins = from_root_file(map_tree_file, roi)

        return cls(data_analysis_bins, roi)

    def __iter__(self):
        """
        This allows to loop over the analysis bins as in:

        for analysis_bin in maptree:

            ... do something ...

        :return: analysis bin_name iterator
        """

        for analysis_bin in self._analysis_bins:

            yield analysis_bin

    def __getitem__(self, item):
        """
        This allows to access the analysis bins by name:

        first_analysis_bin = maptree["bin_name 0"]

        :param item: string for access by name
        :return: the analysis bin_name
        """

        try:

            return self._analysis_bins[item]

        except IndexError:

            raise IndexError("Analysis bin_name with index %i does not exist" % (item))

    def __len__(self):

        return len(self._analysis_bins)

    @property
    def analysis_bins_labels(self):
class SomeClass:
    def some_method(self):
        """Do x and return foo."""

        return self._analysis_bins.keys()

    def display(self):
class SomeClass:
    def some_method(self):
        """Do x and return foo."""

        df = pd.DataFrame()


        df['Bin'] = self._analysis_bins.keys()
        df['Nside'] = [self._analysis_bins[bin_id].nside for bin_id in self._analysis_bins]
        df['Scheme'] = [self._analysis_bins[bin_id].scheme for bin_id in self._analysis_bins]

        # Compute observed counts, background counts, how many pixels we have in the ROI and
        # the sky area they cover
        n_bins = len(self._analysis_bins)

        obs_counts = np.zeros(n_bins)
        bkg_counts = np.zeros_like(obs_counts)
        n_pixels = np.zeros(n_bins, dtype=int)
        sky_area = np.zeros_like(obs_counts)

        size = 0

        for i, bin_id in enumerate(self._analysis_bins):

            analysis_bin = self._analysis_bins[bin_id]

            sparse_obs = analysis_bin.observation_map.as_partial()
            sparse_bkg = analysis_bin.background_map.as_partial()

            size += sparse_obs.nbytes
            size += sparse_bkg.nbytes

            obs_counts[i] = sparse_obs.sum()
            bkg_counts[i] = sparse_bkg.sum()
            n_pixels[i] = sparse_obs.shape[0]
            sky_area[i] = n_pixels[i] * analysis_bin.observation_map.pixel_area

        df['Obs counts'] = obs_counts
        df['Bkg counts'] = bkg_counts
        df['obs/bkg'] = obs_counts / bkg_counts
        df['Pixels in ROI'] = n_pixels
        df['Area (deg^2)'] = sky_area

        display(df)

        first_bin_id = self._analysis_bins.keys()[0]
        print("This Map Tree contains %.3f transits in the first bin" \

            % self._analysis_bins[first_bin_id].n_transits)
        print("Total data size: %.2f Mb" % (size * u.byte).to(u.megabyte).value)


    def write(self, filename):
        """
        Export the tree to a HDF5 file.

        NOTE: if an ROI has been applied, only the data within the ROI will be saved.

        :param filename: output filename. Use an extension .hd5 or .hdf5 to ensure proper handling by downstream
        software
        :return: None
        """

        # Make a dataframe with the ordered list of bin names
        # bin_names = map(lambda x:x.name, self._analysis_bins)

        # Create a dataframe with a multi-index, with the energy bin name as first level and the HEALPIX pixel ID
        # as the second level
        multi_index_keys = []
        dfs = []
        all_metas = []

        for bin_id in self._analysis_bins:

            analysis_bin = self._analysis_bins[bin_id]

            assert bin_id == analysis_bin.name, \
                'Bin name inconsistency: {} != {}'.format(bin_id, analysis_bin.name)

            multi_index_keys.append(analysis_bin.name)

            this_df, this_meta = analysis_bin.to_pandas()

            dfs.append(this_df)
            all_metas.append(pd.Series(this_meta))

        analysis_bins_df = pd.concat(dfs, axis=0, keys=multi_index_keys)
        meta_df = pd.concat(all_metas, axis=1, keys=multi_index_keys).T

        with Serialization(filename, mode='w') as serializer:

            serializer.store_pandas_object('/analysis_bins', analysis_bins_df)
            serializer.store_pandas_object('/analysis_bins_meta', meta_df)

            # Write the ROI
            if self._roi is not None:

                serializer.store_pandas_object('/ROI', pd.Series(), **self._roi.to_dict())

            else:

                serializer.store_pandas_object('/ROI', pd.Series())


1			import os
			0 ignored issues – show Coding Style introduced 2018-07-12 14:17 UTC by Report Bug Copy Issue Report This module should have a docstring. The coding style of this project requires that you add a docstring to this code element. Below, you find an example for methods: class SomeClass: def some_method(self): """Do x and return foo.""" If you would like to know more about docstrings, we recommend to read PEP-257: Docstring Conventions. Loading history...
2			import numpy as np
			0 ignored issues – show introduced 2018-07-12 14:17 UTC by Report Bug Copy Issue Report Unable to import 'numpy' Loading history...
3			import pandas as pd
			0 ignored issues – show introduced 2018-07-12 14:17 UTC by Report Bug Copy Issue Report Unable to import 'pandas' Loading history...
4
5			from threeML.io.rich_display import display
			0 ignored issues – show introduced 2018-06-02 00:48 UTC by Report Bug Copy Issue Report Unable to import 'threeML.io.rich_display' Loading history...
6			from threeML.io.file_utils import sanitize_filename
			0 ignored issues – show introduced 2018-06-02 00:48 UTC by Report Bug Copy Issue Report Unable to import 'threeML.io.file_utils' Loading history...
7
8			from ..serialize import Serialization
9			from from_root_file import from_root_file
			0 ignored issues – show Coding Style introduced 2018-06-02 00:48 UTC by Report Bug Copy Issue Report Relative import 'from_root_file', should be 'hawc_hal.maptree.from_root_file' Loading history... introduced 2018-07-11 05:54 UTC by Report Bug Copy Issue Report first party import "from from_root_file import from_root_file" should be placed before "from ..serialize import Serialization" Loading history...
10			from from_hdf5_file import from_hdf5_file
			0 ignored issues – show Coding Style introduced 2018-06-02 00:48 UTC by Report Bug Copy Issue Report Relative import 'from_hdf5_file', should be 'hawc_hal.maptree.from_hdf5_file' Loading history... introduced 2018-07-11 05:54 UTC by Report Bug Copy Issue Report first party import "from from_hdf5_file import from_hdf5_file" should be placed before "from ..serialize import Serialization" Loading history...
11
12			import astropy.units as u
			0 ignored issues – show introduced 2018-06-02 00:48 UTC by Report Bug Copy Issue Report Unable to import 'astropy.units' Loading history... introduced 2018-07-11 05:54 UTC by Report Bug Copy Issue Report first party import "import astropy.units as u" should be placed before "from ..serialize import Serialization" Loading history...
13
14
15			def map_tree_factory(map_tree_file, roi):
			0 ignored issues – show Coding Style introduced 2018-06-02 00:48 UTC by Report Bug Copy Issue Report This function should have a docstring. The coding style of this project requires that you add a docstring to this code element. Below, you find an example for methods: class SomeClass: def some_method(self): """Do x and return foo.""" If you would like to know more about docstrings, we recommend to read PEP-257: Docstring Conventions. Loading history...
16
17			# Sanitize files in input (expand variables and so on)
18			map_tree_file = sanitize_filename(map_tree_file)
19
20			if os.path.splitext(map_tree_file)[-1] == '.root':
			0 ignored issues – show unused-code introduced 2018-06-02 00:48 UTC by Report Bug Copy Issue Report Unnecessary "else" after "return" Loading history...
21
22			return MapTree.from_root_file(map_tree_file, roi)
23
24			else:
25
26			return MapTree.from_hdf5(map_tree_file, roi)
27
28
29			class MapTree(object):
			0 ignored issues – show Coding Style introduced 2018-06-02 00:48 UTC by Report Bug Copy Issue Report This class should have a docstring. The coding style of this project requires that you add a docstring to this code element. Below, you find an example for methods: class SomeClass: def some_method(self): """Do x and return foo.""" If you would like to know more about docstrings, we recommend to read PEP-257: Docstring Conventions. Loading history...
30
31			def __init__(self, analysis_bins, roi):
32
33			self._analysis_bins = analysis_bins
34			self._roi = roi
35
36			@classmethod
37			def from_hdf5(cls, map_tree_file, roi):
			0 ignored issues – show Coding Style introduced 2018-06-02 00:48 UTC by Report Bug Copy Issue Report This method should have a docstring. The coding style of this project requires that you add a docstring to this code element. Below, you find an example for methods: class SomeClass: def some_method(self): """Do x and return foo.""" If you would like to know more about docstrings, we recommend to read PEP-257: Docstring Conventions. Loading history...
38
39			data_analysis_bins = from_hdf5_file(map_tree_file, roi)
40
41			return cls(data_analysis_bins, roi)
42
43			@classmethod
44			def from_root_file(cls, map_tree_file, roi):
45			"""
46			Create a MapTree object from a ROOT file and a ROI. Do not use this directly, use map_tree_factory instead.
47
48			:param map_tree_file:
49			:param roi:
50			:return:
51			"""
52
53			data_analysis_bins = from_root_file(map_tree_file, roi)
54
55			return cls(data_analysis_bins, roi)
56
57			def __iter__(self):
58			"""
59			This allows to loop over the analysis bins as in:
60
61			for analysis_bin in maptree:
62
63			... do something ...
64
65			:return: analysis bin_name iterator
66			"""
67
68			for analysis_bin in self._analysis_bins:
69
70			yield analysis_bin
71
72			def __getitem__(self, item):
73			"""
74			This allows to access the analysis bins by name:
75
76			first_analysis_bin = maptree["bin_name 0"]
77
78			:param item: string for access by name
79			:return: the analysis bin_name
80			"""
81
82			try:
83
84			return self._analysis_bins[item]
85
86			except IndexError:
87
88			raise IndexError("Analysis bin_name with index %i does not exist" % (item))
89
90			def __len__(self):
91
92			return len(self._analysis_bins)
93
94			@property
95			def analysis_bins_labels(self):
			0 ignored issues – show Coding Style introduced 2018-07-06 22:00 UTC by Report Bug Copy Issue Report This method should have a docstring. The coding style of this project requires that you add a docstring to this code element. Below, you find an example for methods: class SomeClass: def some_method(self): """Do x and return foo.""" If you would like to know more about docstrings, we recommend to read PEP-257: Docstring Conventions. Loading history...
96
97			return self._analysis_bins.keys()
98
99			def display(self):
			0 ignored issues – show Coding Style introduced 2018-06-02 00:48 UTC by Report Bug Copy Issue Report This method should have a docstring. The coding style of this project requires that you add a docstring to this code element. Below, you find an example for methods: class SomeClass: def some_method(self): """Do x and return foo.""" If you would like to know more about docstrings, we recommend to read PEP-257: Docstring Conventions. Loading history...
100
101			df = pd.DataFrame()
			0 ignored issues – show Coding Style Naming introduced 2018-07-11 05:54 UTC by Report Bug Copy Issue Report Variable name "df" doesn't conform to snake_case naming style ('(([a-z_][a-z0-9_]2,30)\|(_[a-z0-9_]*)\|(__[a-z][a-z0-9_]+__))$' pattern) This check looks for invalid names for a range of different identifiers. You can set regular expressions to which the identifiers must conform if the defaults do not match your requirements. If your project includes a Pylint configuration file, the settings contained in that file take precedence. To find out more about Pylint, please refer to their site. Loading history...
102
103			df['Bin'] = self._analysis_bins.keys()
104			df['Nside'] = [self._analysis_bins[bin_id].nside for bin_id in self._analysis_bins]
105			df['Scheme'] = [self._analysis_bins[bin_id].scheme for bin_id in self._analysis_bins]
106
107			# Compute observed counts, background counts, how many pixels we have in the ROI and
108			# the sky area they cover
109			n_bins = len(self._analysis_bins)
110
111			obs_counts = np.zeros(n_bins)
112			bkg_counts = np.zeros_like(obs_counts)
113			n_pixels = np.zeros(n_bins, dtype=int)
114			sky_area = np.zeros_like(obs_counts)
115
116			size = 0
117
118			for i, bin_id in enumerate(self._analysis_bins):
119
120			analysis_bin = self._analysis_bins[bin_id]
121
122			sparse_obs = analysis_bin.observation_map.as_partial()
123			sparse_bkg = analysis_bin.background_map.as_partial()
124
125			size += sparse_obs.nbytes
126			size += sparse_bkg.nbytes
127
128			obs_counts[i] = sparse_obs.sum()
129			bkg_counts[i] = sparse_bkg.sum()
130			n_pixels[i] = sparse_obs.shape[0]
131			sky_area[i] = n_pixels[i] * analysis_bin.observation_map.pixel_area
132
133			df['Obs counts'] = obs_counts
134			df['Bkg counts'] = bkg_counts
135			df['obs/bkg'] = obs_counts / bkg_counts
136			df['Pixels in ROI'] = n_pixels
137			df['Area (deg^2)'] = sky_area
138
139			display(df)
140
141			first_bin_id = self._analysis_bins.keys()[0]
142			print("This Map Tree contains %.3f transits in the first bin" \
			0 ignored issues – show Unused Code Coding Style introduced 2018-07-12 02:41 UTC by Report Bug Copy Issue Report There is an unnecessary parenthesis after `print`. Loading history...
143			% self._analysis_bins[first_bin_id].n_transits)
144			print("Total data size: %.2f Mb" % (size * u.byte).to(u.megabyte).value)
			0 ignored issues – show Unused Code Coding Style introduced 2018-06-02 00:48 UTC by Report Bug Copy Issue Report There is an unnecessary parenthesis after `print`. Loading history...
145
146			def write(self, filename):
147			"""
148			Export the tree to a HDF5 file.
149
150			NOTE: if an ROI has been applied, only the data within the ROI will be saved.
151
152			:param filename: output filename. Use an extension .hd5 or .hdf5 to ensure proper handling by downstream
153			software
154			:return: None
155			"""
156
157			# Make a dataframe with the ordered list of bin names
158			# bin_names = map(lambda x:x.name, self._analysis_bins)
159
160			# Create a dataframe with a multi-index, with the energy bin name as first level and the HEALPIX pixel ID
161			# as the second level
162			multi_index_keys = []
163			dfs = []
164			all_metas = []
165
166			for bin_id in self._analysis_bins:
167
168			analysis_bin = self._analysis_bins[bin_id]
169
170			assert bin_id == analysis_bin.name, \
171			'Bin name inconsistency: {} != {}'.format(bin_id, analysis_bin.name)
172
173			multi_index_keys.append(analysis_bin.name)
174
175			this_df, this_meta = analysis_bin.to_pandas()
176
177			dfs.append(this_df)
178			all_metas.append(pd.Series(this_meta))
179
180			analysis_bins_df = pd.concat(dfs, axis=0, keys=multi_index_keys)
181			meta_df = pd.concat(all_metas, axis=1, keys=multi_index_keys).T
182
183			with Serialization(filename, mode='w') as serializer:
184
185			serializer.store_pandas_object('/analysis_bins', analysis_bins_df)
186			serializer.store_pandas_object('/analysis_bins_meta', meta_df)
187
188			# Write the ROI
189			if self._roi is not None:
190
191			serializer.store_pandas_object('/ROI', pd.Series(), **self._roi.to_dict())
192
193			else:
194
195			serializer.store_pandas_object('/ROI', pd.Series())
196

giacomov / hawc_hal

Push — master ( 20ef60...3972dc )

hawc_hal.maptree.map_tree.MapTree.write() B

Complexity

Size

Duplication

Importance

Duplication Side-by-Side

Filter issues like