Merge pull request #17 from mruffalo/python3

Support Python 2.7, 3.4, 3.5, 3.6

.gitignore

@@ -0,0 +1 @@
+__pycache__/

.travis.yml

@@ -3,6 +3,9 @@ language: python
 # python versioning 
 python:
   - 2.7
+  - 3.4
+  - 3.5
+  - 3.6
 
 # requirements
 install: 

cmapPy/__init__.py

@@ -1,3 +1,3 @@
-from clue_api_client import *
-from pandasGEXpress import *
-from set_io import *
+from .clue_api_client import *
+from .pandasGEXpress import *
+from .set_io import *

cmapPy/clue_api_client/cell_queries.py

@@ -1,5 +1,5 @@
 import logging
-import setup_logger
+from . import setup_logger
 
 __authors__ = "David L. Lahr"
 __email__ = "dlahr@broadinstitute.org"

cmapPy/clue_api_client/clue_api_client.py

@@ -1,6 +1,6 @@
 import requests
 import logging
-import setup_logger
+from . import setup_logger
 import json
 import copy
 

cmapPy/clue_api_client/gene_queries.py

@@ -1,5 +1,5 @@
 import logging
-import setup_logger
+from . import setup_logger
 
 __authors__ = "David L. Lahr"
 __email__ = "dlahr@broadinstitute.org"

cmapPy/clue_api_client/macchiato_queries.py

@@ -1,5 +1,5 @@
 import logging
-import setup_logger
+from . import setup_logger
 
 __authors__ = "David L. Lahr"
 __email__ = "dlahr@broadinstitute.org"

cmapPy/clue_api_client/mock_clue_api_client.py

@@ -1,6 +1,6 @@
 import logging
-import setup_logger
-import clue_api_client
+from . import setup_logger
+from . import clue_api_client
 
 __authors__ = "David L. Lahr"
 __email__ = "dlahr@broadinstitute.org"

cmapPy/clue_api_client/pert_queries.py

@@ -1,5 +1,5 @@
 import logging
-import setup_logger
+from . import setup_logger
 
 __authors__ = "David L. Lahr"
 __email__ = "dlahr@broadinstitute.org"

cmapPy/clue_api_client/tests/test_clue_api_client.py

@@ -3,9 +3,10 @@
 import logging
 from cmapPy.clue_api_client import clue_api_client as clue_api_client
 import os.path
-import ConfigParser
 import collections
 
+from six.moves import configparser
+
 __authors__ = "David L. Lahr"
 __email__ = "dlahr@broadinstitute.org"
 
@@ -120,7 +121,7 @@ def test_run_put(self):
 
 
 def build_clue_api_client_from_default_test_config():
-    cfg = ConfigParser.RawConfigParser()
+    cfg = configparser.RawConfigParser()
     cfg.read(config_filepath)
     cao = clue_api_client.ClueApiClient(base_url=cfg.get(config_section, "clue_api_url"),
                                   user_key=cfg.get(config_section, "clue_api_user_key"))

cmapPy/clue_api_client/tests/test_pert_queries.py

@@ -18,9 +18,9 @@ def test__build_map_from_clue_api_result(self):
         r = pq._build_map_from_clue_api_result([{"a": "b", "c": "d"}], "a", "c")
         self.assertIsNotNone(r)
         logger.debug("r:  {}".format(r))
-        self.assertEquals(1, len(r))
+        self.assertEqual(1, len(r))
         self.assertIn("b", r)
-        self.assertEquals("d", r["b"])
+        self.assertEqual("d", r["b"])
 
     def test_retrieve_pert_id_pert_iname_map(self):
         r = pq.retrieve_pert_id_pert_iname_map(["BRD-K21680192", "BRD-K88378636", "not a valid BRD"], cao)

cmapPy/pandasGEXpress/GCToo.py

@@ -42,7 +42,7 @@
 import numpy as np
 import pandas as pd
 import logging
-import setup_GCToo_logger as setup_logger
+from . import setup_GCToo_logger as setup_logger
 
 
 __authors__ = 'Oana Enache, Lev Litichevskiy, Dave Lahr'

cmapPy/pandasGEXpress/concat_gctoo.py

@@ -36,14 +36,16 @@
 import sys
 import glob
 import logging
-import setup_GCToo_logger as setup_logger
-import pandas as pd
+
 import numpy
+import pandas as pd
+from six.moves import range
 
-import GCToo
-import parse 
-import write_gct
-import write_gctx 
+from . import GCToo
+from . import parse
+from . import setup_GCToo_logger as setup_logger
+from . import write_gct
+from . import write_gctx
 
 __author__ = "Lev Litichevskiy"
 __email__ = "lev@broadinstitute.org"
@@ -371,7 +373,7 @@ def build_mismatched_common_meta_report(common_meta_df_shapes, sources, all_meta
     expanded_sources = []
     for (i, shape) in enumerate(common_meta_df_shapes):
         src = sources[i]
-        expanded_sources.extend([src for i in xrange(shape[0])])
+        expanded_sources.extend([src for i in range(shape[0])])
     expanded_sources = numpy.array(expanded_sources)
     logger.debug("len(expanded_sources):  {}".format(len(expanded_sources)))
 
@@ -386,8 +388,8 @@ def build_mismatched_common_meta_report(common_meta_df_shapes, sources, all_meta
     for unique_dup_id in unique_duplicate_ids:
         rows = duplicate_ids_meta_df.loc[unique_dup_id]
 
-        matching_row_locs = numpy.array([False for i in xrange(all_meta_df_with_dups.shape[0])])
-        for i in xrange(rows.shape[0]):
+        matching_row_locs = numpy.array([False for i in range(all_meta_df_with_dups.shape[0])])
+        for i in range(rows.shape[0]):
             r = rows.iloc[i]
             row_comparison = r == all_meta_df_with_dups
             matching_row_locs = matching_row_locs | row_comparison.all(axis=1).values
@@ -399,7 +401,7 @@ def build_mismatched_common_meta_report(common_meta_df_shapes, sources, all_meta
 
     all_report_df = pd.concat(report_df_list, axis=0)
     all_report_df["orig_rid"] = all_report_df.index
-    all_report_df.index = pd.Index(xrange(all_report_df.shape[0]), name="index")
+    all_report_df.index = pd.Index(range(all_report_df.shape[0]), name="index")
     logger.debug("all_report_df.shape:  {}".format(all_report_df.shape))
     logger.debug("all_report_df.index:  {}".format(all_report_df.index))
     logger.debug("all_report_df.columns:  {}".format(all_report_df.columns))

cmapPy/pandasGEXpress/gct2gctx.py

@@ -9,11 +9,11 @@
 """
 
 import logging
-import setup_GCToo_logger as setup_logger
+from . import setup_GCToo_logger as setup_logger
 import argparse
 import sys
-import parse_gct
-import write_gctx
+from . import parse_gct
+from . import write_gctx
 
 __author__ = "Oana Enache"
 __email__ = "oana@broadinstitute.org"

cmapPy/pandasGEXpress/gctx2gct.py

@@ -9,11 +9,11 @@
 """
 
 import logging
-import setup_GCToo_logger as setup_logger
+from . import setup_GCToo_logger as setup_logger
 import argparse
 import sys
-import parse_gctx
-import write_gct
+from . import parse_gctx
+from . import write_gct
 import os.path
 
 __author__ = "Oana Enache"

cmapPy/pandasGEXpress/mini_gctoo_for_testing.py

@@ -7,10 +7,10 @@
 """
 
 import logging
-import setup_GCToo_logger as setup_logger
+from . import setup_GCToo_logger as setup_logger
 import pandas
 import numpy
-import GCToo
+from . import GCToo
 
 __author__ = 'Oana Enache'
 __email__ = 'oana@broadinstitute.org'

cmapPy/pandasGEXpress/parse.py

@@ -8,9 +8,9 @@
 """
 
 import logging
-import setup_GCToo_logger as setup_logger
-import parse_gct
-import parse_gctx
+from . import setup_GCToo_logger as setup_logger
+from . import parse_gct
+from . import parse_gctx
 
 __author__ = "Oana Enache"
 __email__ = "oana@broadinstitute.org"

cmapPy/pandasGEXpress/parse_gct.py

@@ -60,11 +60,11 @@
 """
 
 import logging
-import setup_GCToo_logger as setup_logger
+from . import setup_GCToo_logger as setup_logger
 import pandas as pd
-import numpy as np 
+import numpy as np
 import os.path
-import GCToo 
+from . import GCToo
 
 __author__ = "Lev Litichevskiy, Oana Enache"
 __email__ = "lev@broadinstitute.org"
@@ -115,7 +115,7 @@ def parse(file_path, convert_neg_666=True, row_meta_only=False, col_meta_only=Fa
     if not os.path.exists(file_path):
         err_msg = "The given path to the gct file cannot be found. gct_path: {}"
         logger.error(err_msg.format(file_path))
-        raise(Exception(err_msg.format(file_path)))
+        raise Exception(err_msg.format(file_path))
     logger.info("Reading GCT: {}".format(file_path))
 
     # Read version and dimensions
@@ -150,7 +150,7 @@ def read_version_and_dims(file_path):
         err_msg = ("Only GCT1.2 and 1.3 are supported. The first row of the GCT " +
                    "file must simply be (without quotes) '#1.3' or '#1.2'")
         logger.error(err_msg.format(version))
-        raise(Exception(err_msg.format(version)))
+        raise Exception(err_msg.format(version))
 
     # Convert version to a string
     version_as_string = "GCT" + str(version)
@@ -165,11 +165,11 @@ def read_version_and_dims(file_path):
     if version == "1.2" and len(dims) != 2:
         error_msg = "GCT1.2 should have 2 dimension-related entries in row 2. dims: {}"
         logger.error(error_msg.format(dims))
-        raise(Exception(error_msg.format(dims)))
-    elif version == "1.3" and len(dims) != 4: 
+        raise Exception(error_msg.format(dims))
+    elif version == "1.3" and len(dims) != 4:
         error_msg = "GCT1.3 should have 4 dimension-related entries in row 2. dims: {}"
         logger.error(error_msg.format(dims))
-        raise(Exception(error_msg.format(dims)))
+        raise Exception(error_msg.format(dims))
 
     # Explicitly define each dimension
     num_data_rows = int(dims[0])
@@ -286,7 +286,7 @@ def assemble_data(full_df, num_col_metadata, num_data_rows, num_row_metadata, nu
                                    "data.loc['{}', '{}'] = '{}'\nAdd to nan_values if you wish " +
                                    "for this value to be considered NaN.").format(bad_row_label, col, val)
                         logger.error(err_msg)
-                        raise(Exception(err_msg))
+                        raise Exception(err_msg)
 
     # Rename the index name and columns name
     data.index.name = row_index_name

cmapPy/pandasGEXpress/parse_gctx.py

@@ -1,10 +1,10 @@
 import logging
-import setup_GCToo_logger as setup_logger
+from . import setup_GCToo_logger as setup_logger
 import os
 import numpy as np
 import pandas as pd
 import h5py
-import GCToo
+from . import GCToo
 
 __author__ = "Oana Enache"
 __email__ = "oana@broadinstitute.org"
@@ -58,7 +58,7 @@ def parse(gctx_file_path, convert_neg_666=True, rid=None, cid=None,
     if not os.path.exists(full_path):
         err_msg = "The given path to the gctx file cannot be found. full_path: {}"
         logger.error(err_msg.format(full_path))
-        raise (Exception(err_msg.format(full_path)))
+        raise Exception(err_msg.format(full_path))
     logger.info("Reading GCTX: {}".format(full_path))
 
     # open file

cmapPy/pandasGEXpress/random_slice.py

@@ -2,9 +2,9 @@
 Slices a random subset of a GCToo instance of a user-specified size. 
 """
 import logging
-import setup_GCToo_logger as setup_logger
+from . import setup_GCToo_logger as setup_logger
 import numpy
-import GCToo
+from . import GCToo
 
 __author__ = "Oana Enache"
 __email__ = "oana@broadinstitute.org"

cmapPy/pandasGEXpress/slice_gct.py

@@ -14,10 +14,10 @@
 import pandas as pd
 import re
 
-import setup_GCToo_logger as setup_logger
-import GCToo 
-import parse_gct as pg
-import write_gct as wg
+from . import setup_GCToo_logger as setup_logger
+from . import GCToo
+from . import parse_gct as pg
+from . import write_gct as wg
 
 __author__ = "Lev Litichevskiy"
 __email__ = "lev@broadinstitute.org"
@@ -190,4 +190,4 @@ def slice_gctoo(gctoo, row_bool=None, col_bool=None, rid=None, cid=None, exclude
 
 
 if __name__ == "__main__":
-    main()
+    main()

cmapPy/pandasGEXpress/tests/test_concat_gctoo.py

@@ -1,3 +1,5 @@
+from __future__ import print_function
+
 import os
 import unittest
 import logging
@@ -369,9 +371,9 @@ def parse_args(self, unused):
 
         os.remove(expected_output_file)
 
-        print
-        print
-        print
+        print()
+        print()
+        print()
 
         #happy path
         args.remove_all_metadata_fields = True