From 8000642e3a9bde66c90a029e96239f70d51776b3 Mon Sep 17 00:00:00 2001 From: Milton Pividori Date: Mon, 4 May 2020 11:56:32 -0400 Subject: [PATCH] utils package moved into clustermatch. --- README.md | 2 +- clustermatch/__init__.py | 2 +- clustermatch/main.py | 6 +++--- {utils => clustermatch/utils}/__init__.py | 0 {utils => clustermatch/utils}/data.py | 0 {utils => clustermatch/utils}/html/color-hash.js | 0 {utils => clustermatch/utils}/html/index.html | 0 {utils => clustermatch/utils}/methods.py | 0 {utils => clustermatch/utils}/misc.py | 0 {utils => clustermatch/utils}/output.py | 2 +- environment.yml | 4 ++-- environment_full.yml | 4 ++-- experiments/execution.py | 2 +- experiments/methods.py | 2 +- experiments/tomato/main.py | 9 +++------ experiments/tomato/main_find_k.py | 4 ++-- setup.py | 4 ++-- tests/clustermatch/test_clustermatch.py | 2 +- tests/clustermatch/test_clustermatch_simmatrix.py | 5 ++--- tests/test_merge_sources.py | 2 +- 20 files changed, 23 insertions(+), 27 deletions(-) rename {utils => clustermatch/utils}/__init__.py (100%) rename {utils => clustermatch/utils}/data.py (100%) rename {utils => clustermatch/utils}/html/color-hash.js (100%) rename {utils => clustermatch/utils}/html/index.html (100%) rename {utils => clustermatch/utils}/methods.py (100%) rename {utils => clustermatch/utils}/misc.py (100%) rename {utils => clustermatch/utils}/output.py (99%) diff --git a/README.md b/README.md index fa789d5..9fc0db4 100644 --- a/README.md +++ b/README.md @@ -149,7 +149,7 @@ $ cd {CLUSTERMATCH_FOLDER} $ ipython ``` ```python -In [1]: from utils.data import merge_sources +In [1]: from clustermatch.utils.data import merge_sources In [2]: from clustermatch.cluster import calculate_simmatrix, get_partition_spectral In [3]: data_files = ['experiments/tomato/data/real_sample.xlsx'] In [4]: merged_sources, feature_names, sources_names = merge_sources(data_files) diff --git a/clustermatch/__init__.py b/clustermatch/__init__.py index 90e0585..fe5e8f9 100644 --- a/clustermatch/__init__.py +++ b/clustermatch/__init__.py @@ -1,2 +1,2 @@ -__version__ = '0.1.4a3' +__version__ = '0.1.5' __short_description__ = 'Efficient clustering method for processing highly diverse data' diff --git a/clustermatch/main.py b/clustermatch/main.py index 0cb0299..54a2620 100644 --- a/clustermatch/main.py +++ b/clustermatch/main.py @@ -2,9 +2,9 @@ import logging from clustermatch import __short_description__ -from clustermatch.cluster import calculate_simmatrix, get_partition_spectral, get_pval_matrix_by_partition -from utils.data import merge_sources -from utils.output import save_partitions_simple +from clustermatch.cluster import calculate_simmatrix, get_partition_spectral +from clustermatch.utils.data import merge_sources +from clustermatch.utils.output import save_partitions_simple LOG_FORMAT = "[%(asctime)s] %(levelname)s: %(message)s" logging.basicConfig(format=LOG_FORMAT, level=logging.INFO) diff --git a/utils/__init__.py b/clustermatch/utils/__init__.py similarity index 100% rename from utils/__init__.py rename to clustermatch/utils/__init__.py diff --git a/utils/data.py b/clustermatch/utils/data.py similarity index 100% rename from utils/data.py rename to clustermatch/utils/data.py diff --git a/utils/html/color-hash.js b/clustermatch/utils/html/color-hash.js similarity index 100% rename from utils/html/color-hash.js rename to clustermatch/utils/html/color-hash.js diff --git a/utils/html/index.html b/clustermatch/utils/html/index.html similarity index 100% rename from utils/html/index.html rename to clustermatch/utils/html/index.html diff --git a/utils/methods.py b/clustermatch/utils/methods.py similarity index 100% rename from utils/methods.py rename to clustermatch/utils/methods.py diff --git a/utils/misc.py b/clustermatch/utils/misc.py similarity index 100% rename from utils/misc.py rename to clustermatch/utils/misc.py diff --git a/utils/output.py b/clustermatch/utils/output.py similarity index 99% rename from utils/output.py rename to clustermatch/utils/output.py index a33f41d..7df8e25 100644 --- a/utils/output.py +++ b/clustermatch/utils/output.py @@ -23,7 +23,7 @@ except: REQUESTS_INSTALLED = False -from utils.misc import get_temp_file_name +from clustermatch.utils.misc import get_temp_file_name RESULTS_DIR = 'results' diff --git a/environment.yml b/environment.yml index 6617bdb..bc2561a 100644 --- a/environment.yml +++ b/environment.yml @@ -4,12 +4,12 @@ channels: dependencies: - tabulate=0.8 - ipython=6.2 -- joblib=0.11 +- joblib=0.12 - numpy=1.13 - pandas=0.21 - python=3.6 - scikit-learn=0.19 - scipy=1.0.0 - xlrd=1.1 -- xlwt=1.2 +- xlwt=1.3 - openpyxl=2.4 diff --git a/environment_full.yml b/environment_full.yml index 4e2ecf5..1fe149a 100644 --- a/environment_full.yml +++ b/environment_full.yml @@ -5,7 +5,7 @@ dependencies: - tabulate=0.8 - requests=2.18 - ipython=6.2 -- joblib=0.11 +- joblib=0.12 - matplotlib=2.1 - numpy=1.13 - pandas=0.21 @@ -14,7 +14,7 @@ dependencies: - scipy=1.0.0 - seaborn=0.8 - xlrd=1.1 -- xlwt=1.2 +- xlwt=1.3 - openpyxl=2.4 - pillow=5.1 - pip: diff --git a/experiments/execution.py b/experiments/execution.py index 2c9e383..2f59bcb 100644 --- a/experiments/execution.py +++ b/experiments/execution.py @@ -7,7 +7,7 @@ from sklearn.metrics import adjusted_rand_score as ari, adjusted_mutual_info_score as ami from tabulate import tabulate -from utils.output import get_timestamp +from clustermatch.utils.output import get_timestamp def _run_experiment(rep_number, data_generator, methods, k_final=None, data_transform=None, data_noise=None, diff --git a/experiments/methods.py b/experiments/methods.py index 975041b..0a36c38 100644 --- a/experiments/methods.py +++ b/experiments/methods.py @@ -10,7 +10,7 @@ from pyclustering.cluster.optics import optics from clustermatch.cluster import cm, calculate_simmatrix, get_partition_spectral -from utils.methods import distcorr +from clustermatch.utils.methods import distcorr SPECTRAL_METHOD = 'spectral' diff --git a/experiments/tomato/main.py b/experiments/tomato/main.py index 33a3379..30120f4 100644 --- a/experiments/tomato/main.py +++ b/experiments/tomato/main.py @@ -7,12 +7,9 @@ import numpy as np -from clustermatch.cluster import calculate_simmatrix, get_partition_spectral, get_normalized_sim_matrix, \ - get_pval_matrix_by_partition, get_sim_matrix_by_partition -from utils.data import merge_sources -from utils.output import get_timestamp, save_partitions, create_partition_plot_html, to_binary, get_clustergrammer_link, \ - save_excel, write_data_description, append_data_description - +from clustermatch.cluster import calculate_simmatrix, get_partition_spectral, get_pval_matrix_by_partition, get_sim_matrix_by_partition +from clustermatch.utils.data import merge_sources +from clustermatch.utils.output import save_partitions, create_partition_plot_html, save_excel, write_data_description BASE_DATA_DIR = 'data' diff --git a/experiments/tomato/main_find_k.py b/experiments/tomato/main_find_k.py index f8c5fd8..6d437cd 100644 --- a/experiments/tomato/main_find_k.py +++ b/experiments/tomato/main_find_k.py @@ -9,8 +9,8 @@ from clustermatch.cluster import get_partition_spectral, calculate_simmatrix -from utils.data import merge_sources -from utils.output import to_binary, write_text_file +from clustermatch.utils.data import merge_sources +from clustermatch.utils.output import to_binary, write_text_file def sc(sim_matrix, k): diff --git a/setup.py b/setup.py index 60b4f3a..8c38f8e 100644 --- a/setup.py +++ b/setup.py @@ -8,13 +8,13 @@ name="clustermatch", version=__version__, author="Milton Pividori", - author_email="miltondp@uchicago.edu", + author_email="miltondp@gmail.com", description=__short_description__, license='MIT', long_description=long_description, long_description_content_type="text/markdown", url="https://github.com/sinc-lab/clustermatch", - packages=['clustermatch', 'utils'], + packages=['clustermatch', 'clustermatch/utils'], python_requires='>=3', install_requires=[ 'numpy', diff --git a/tests/clustermatch/test_clustermatch.py b/tests/clustermatch/test_clustermatch.py index 1b51a18..a6834aa 100644 --- a/tests/clustermatch/test_clustermatch.py +++ b/tests/clustermatch/test_clustermatch.py @@ -4,7 +4,7 @@ from sklearn.metrics import adjusted_rand_score as ari from clustermatch.cluster import clustermatch, calculate_simmatrix, get_partition_agglomerative, get_partition_spectral -from utils.data import merge_sources +from clustermatch.utils.data import merge_sources from tests.utils import get_data_file diff --git a/tests/clustermatch/test_clustermatch_simmatrix.py b/tests/clustermatch/test_clustermatch_simmatrix.py index 19eca01..da877e7 100644 --- a/tests/clustermatch/test_clustermatch_simmatrix.py +++ b/tests/clustermatch/test_clustermatch_simmatrix.py @@ -5,12 +5,11 @@ from time import time import numpy as np -from scipy.spatial.distance import squareform, pdist -from sklearn.metrics import adjusted_rand_score as ari +from scipy.spatial.distance import squareform from clustermatch.cluster import calculate_simmatrix, get_squareform, run_quantile_clustering from tests.utils import get_data_file -from utils.data import merge_sources +from clustermatch.utils.data import merge_sources class ClusterMatchSimilarityMatrixTest(unittest.TestCase): diff --git a/tests/test_merge_sources.py b/tests/test_merge_sources.py index f81a99d..b54409c 100644 --- a/tests/test_merge_sources.py +++ b/tests/test_merge_sources.py @@ -5,7 +5,7 @@ import numpy as np import pandas as pd -from utils.data import merge_sources +from clustermatch.utils.data import merge_sources from .utils import get_data_file