use scprep

KrishnaswamyLab · Sep 3, 2018 · bc6ea1b · bc6ea1b
1 parent 6035c0a
commit bc6ea1b
Show file tree

Hide file tree

Showing 3 changed files with 34 additions and 11 deletions.
diff --git a/python/magic/io.py b/python/magic/io.py
@@ -203,6 +203,9 @@ def load_csv(filename, cell_axis='row', delimiter=',',
     -------
     data : pd.DataFrame
     """
+    warnings.warn("magic.io is deprecated. Please use scprep.io instead. "
+                  "Read more at http://scprep.readthedocs.io",
+                  FutureWarning)
     if cell_axis not in ['row', 'column', 'col']:
         raise ValueError(
             "cell_axis {} not recognized. Expected 'row' or 'column'".format(
@@ -309,6 +312,9 @@ def load_fcs(filename, gene_names=True, cell_names=True,
     -------
     data : pd.DataFrame
     """
+    warnings.warn("magic.io is deprecated. Please use scprep.io instead. "
+                  "Read more at http://scprep.readthedocs.io",
+                  FutureWarning)
     if cell_names is True:
         cell_names = None
     if gene_names is True:
@@ -347,6 +353,9 @@ def load_mtx(mtx_file, cell_axis='row',
     -------
     data : pd.DataFrame
     """
+    warnings.warn("magic.io is deprecated. Please use scprep.io instead. "
+                  "Read more at http://scprep.readthedocs.io",
+                  FutureWarning)
     if cell_axis not in ['row', 'column', 'col']:
         raise ValueError(
             "cell_axis {} not recognized. Expected 'row' or 'column'".format(
@@ -435,6 +444,9 @@ def load_10X(data_dir, sparse=True, gene_labels='symbol',
     data: pandas.DataFrame shape = (n_cell, n_genes)
         imported data matrix
     """
+    warnings.warn("magic.io is deprecated. Please use scprep.io instead. "
+                  "Read more at http://scprep.readthedocs.io",
+                  FutureWarning)
 
     if gene_labels not in ['id', 'symbol', 'both']:
         raise ValueError("gene_labels not in ['id', 'symbol', 'both']")
@@ -551,6 +563,9 @@ def load_10X_HDF5(filename, genome=None, sparse=True, gene_labels='symbol',
         If sparse, data will be a pd.SparseDataFrame. Otherwise, data will
         be a pd.DataFrame.
     """
+    warnings.warn("magic.io is deprecated. Please use scprep.io instead. "
+                  "Read more at http://scprep.readthedocs.io",
+                  FutureWarning)
     with tables.open_file(filename, 'r') as f:
         if genome is None:
             genomes = [node._v_name for node in f.list_nodes(f.root)]

diff --git a/python/magic/preprocessing.py b/python/magic/preprocessing.py
@@ -6,6 +6,7 @@
 import numpy as np
 from scipy import sparse
 import pandas as pd
+import warnings
 
 
 def library_size_normalize(data, verbose=False):
@@ -25,6 +26,10 @@ def library_size_normalize(data, verbose=False):
     data_norm : ndarray [n, p]
         2 dimensional array with normalized gene expression values
     """
+    warnings.warn("magic.preprocessing is deprecated. "
+                  "Please use scprep.normalize instead. "
+                  "Read more at http://scprep.readthedocs.io",
+                  FutureWarning)
     if verbose:
         print("Normalizing library sizes for %s cells" % (data.shape[0]))
 

diff --git a/python/magic/test.py b/python/magic/test.py
@@ -3,8 +3,8 @@
 
 from __future__ import print_function, division, absolute_import
 import magic
-import pandas as pd
 import numpy as np
+import scprep
 try:
     import anndata
 except (ImportError, SyntaxError):
@@ -13,23 +13,26 @@
 
 
 def test_scdata():
-    scdata = pd.read_csv("../data/test_data.csv")
-    scdata_norm = magic.preprocessing.library_size_normalize(scdata)
+    scdata = scprep.io.read_csv("../data/test_data.csv")
+    scdata_norm = scprep.filter.remove_empty_cells(scdata)
+    scdata_norm = scprep.filter.remove_empty_genes(scdata)
+    scdata_norm = scprep.normalize.library_size_normalize(scdata_norm)
+    scdata_norm = scprep.transform.sqrt(scdata_norm)
     assert scdata.shape == scdata_norm.shape
-    fast_magic_operator = magic.MAGIC(t='auto', a=20, k=10)
-    str_gene_magic = fast_magic_operator.fit_transform(
+    magic_op = magic.MAGIC(t='auto', a=20, k=10)
+    str_gene_magic = magic_op.fit_transform(
         scdata_norm, genes=['VIM', 'ZEB1'])
-    int_gene_magic = fast_magic_operator.fit_transform(
+    int_gene_magic = magic_op.fit_transform(
         scdata_norm, genes=[-2, -1])
     assert str_gene_magic.shape[0] == scdata_norm.shape[0]
     assert np.all(str_gene_magic == int_gene_magic)
-    pca_magic = fast_magic_operator.fit_transform(
+    pca_magic = magic_op.fit_transform(
         scdata_norm, genes="pca_only")
     assert pca_magic.shape[0] == scdata_norm.shape[0]
-    assert pca_magic.shape[1] == fast_magic_operator.n_pca
-    fast_magic = fast_magic_operator.fit_transform(scdata_norm,
-                                                   genes="all_genes")
-    assert scdata_norm.shape == fast_magic.shape
+    assert pca_magic.shape[1] == magic_op.n_pca
+    magic_all_genes = magic_op.fit_transform(scdata_norm,
+                                             genes="all_genes")
+    assert scdata_norm.shape == magic_all_genes.shape
 
 
 def test_anndata():