utils package moved into clustermatch.

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)

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'

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)

utils/output.py → 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'

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

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:

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,

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'

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'
 

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):

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',

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
 
 

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):

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