Merge pull request #1 from 444thLiao/master

reorganized whole project and fullfill setup

setup.py

@@ -0,0 +1,27 @@
+from setuptools import setup, find_packages
+
+setup(name='tmap',
+      version='1.0',
+      description='mapper ',
+      author='Haokui Zhou',
+      author_email='[email protected]',
+      license='GNU',
+      url='https://github.com/GPZ-Bioinfo/tmap',
+      packages=find_packages(),
+      package_data={'': ['test_data/*.csv',
+                         'test_data/*.tsv',
+                         'example/*'],
+                    },
+      install_requires=['statsmodels>=0.9.0',
+                        'tqdm',
+                        'scikit-learn>=0.19.1',
+                        'matplotlib>=2.2.2',
+                        'networkx==1.11',
+                        'pandas>=0.23.0',
+                        'numpy>=1.10.4',
+                        'scipy',
+
+                        ],
+      zip_safe=False,
+      extras_require={'alldeps': ('numpy>=1.10.4', 'scipy',)}
+      )

tda/filter.py → tmap/tda/filter.py

@@ -1,7 +1,7 @@
 # -*- coding: utf-8 -*-
 import numpy as np
 from sklearn import decomposition, manifold
-from tda.metric import Metric
+from tmap.tda.metric import Metric
 
 
 _METRIC_BUILT_IN = ["braycurtis", "canberra", "chebyshev", "cityblock", "correlation", "cosine", "dice", "euclidean",

tda/mapper.py → tmap/tda/mapper.py

@@ -1,9 +1,8 @@
 # -*- coding: utf-8 -*-
-from tda.cover import Cover
 import numpy as np
 import pandas as pd
 import itertools
-from sklearn import cluster, preprocessing
+from sklearn import cluster
 
 
 class Mapper(object):

tda/plot.py → tmap/tda/plot.py

@@ -40,7 +40,10 @@ def __init__(self, target, dtype="numerical", target_by="sample"):
         if target_by not in ["sample", "node"]:
             raise ValueError("target values must be by 'sample' or 'node'")
         # target values should be numbers, check and encode categorical labels
-        if ((type(target[0][0]) != int) and (type(target[0][0]) != float)):
+        if ((type(target[0][0]) != int)
+                and (type(target[0][0]) != float)
+                and (not isinstance(target[0][0],np.number))
+        ):
             self.label_encoder = LabelEncoder()
             self.target = self.label_encoder.fit_transform(target)
         else:
@@ -165,7 +168,10 @@ def show(data, graph, color=None, fig_size=(10, 10), node_size=10, edge_width=2,
     if color.dtype == "categorical":
         for label in set([it[0] for it in color.labels]):
             if color.label_encoder:
-                label_color = legend_lookup[color.label_encoder.fit_transform(label)]
+                try:
+                    label_color = legend_lookup[color.label_encoder.fit_transform(label)]
+                except:
+                    import pdb;pdb.set_trace()
             else:
                 label_color = legend_lookup[label]
             ax.plot([], [], 'o', color=label_color, label=label, markersize=10)

test/test_FGFP.py → tmap/test/test_FGFP.py

@@ -1,13 +1,13 @@
-from sklearn.preprocessing import MinMaxScaler, LabelEncoder, Imputer
+import os
+from sklearn.preprocessing import MinMaxScaler
 from sklearn.cluster import DBSCAN
-import numpy as np
-from tda import mapper, filter
-from tda.cover import Cover
-from tda.plot import show, Color
-from tda.metric import Metric
-from tda.utils import optimize_dbscan_eps
-from netx.SAFE import SAFE_batch, get_SAFE_summary, SAFE_single
-from test import load_data
+from tmap.tda import mapper, filter
+from tmap.tda.cover import Cover
+from tmap.tda.plot import show, Color
+from tmap.tda.metric import Metric
+from tmap.tda.utils import optimize_dbscan_eps
+from tmap.netx.SAFE import SAFE_batch, get_SAFE_summary
+from tmap.test import load_data
 
 
 # load taxa abundance data, sample metadata and precomputed distance matrix
@@ -52,4 +52,4 @@
 
 safe_summary = get_SAFE_summary(graph=graph, meta_data=X, safe_scores=safe_scores,
                                 n_iter_value=n_iter, p_value=0.01)
-safe_summary.to_csv('../example/FGFP_SAFE_ranking_genus_1000.csv', index=True)
+safe_summary.to_csv(os.path.join(os.path.dirname(__file__),'../example/FGFP_SAFE_ranking_genus_1000.csv'), index=True)

test/test_circles.py → tmap/test/test_circles.py

@@ -1,8 +1,8 @@
 from sklearn import datasets
 from sklearn.cluster import DBSCAN
-from tda import mapper, filter
-from tda.cover import Cover
-from tda.plot import show, Color
+from tmap.tda import mapper, filter
+from tmap.tda.cover import Cover
+from tmap.tda.plot import show, Color
 
 
 X, y = datasets.make_circles(n_samples=5000, noise=0.05, factor=0.3)

test/test_digits.py → tmap/test/test_digits.py

@@ -1,9 +1,9 @@
 from sklearn import datasets
 from sklearn.preprocessing import MinMaxScaler
-from tda import mapper, filter
-from tda.cover import Cover
+from tmap.tda import mapper, filter
+from tmap.tda.cover import Cover
 from sklearn.cluster import DBSCAN
-from tda.plot import Color, show
+from tmap.tda.plot import Color, show
 
 
 digits = datasets.load_digits()

test/test_iris.py → tmap/test/test_iris.py

@@ -1,9 +1,9 @@
 from sklearn.preprocessing import MinMaxScaler, StandardScaler
 from sklearn import datasets
 from sklearn.cluster import DBSCAN
-from tda import mapper, filter
-from tda.cover import Cover
-from tda.plot import show, Color
+from tmap.tda import mapper, filter
+from tmap.tda.cover import Cover
+from tmap.tda.plot import show, Color
 
 
 iris = datasets.load_iris()