cpgtools 2.0.2__py3-none-any.whl → 2.0.3__py3-none-any.whl

{cpgtools-2.0.2.data → cpgtools-2.0.3.data}/scripts/dmc_ttest.py

@@ -189,7 +189,7 @@ def main():
 			else:
 				continue
 		line_num += 1
-
+	
 	printlog("Perfrom Benjamini-Hochberg (aka FDR) correction ...")
 	adjusted_p = {}
 	q_list =  padjust.multiple_testing_correction(p_list)
@@ -204,6 +204,10 @@ def main():
 		else:
 			f = l.split()
 			probe_ID = f[0]
+			if probe_ID in delta_beta:
+				pass
+			else:
+				delta_beta[probe_ID] = 'n/a'
 			try:
 				print (l + '\t' + str(delta_beta[probe_ID]) + '\t' + adjusted_p[probe_ID], file=FOUT)
 			except:

cpgtools-2.0.2.data/scripts/beta_imputation.py → cpgtools-2.0.3.data/scripts/predict_missing.py

@@ -20,6 +20,7 @@ from impyute.cs.em import em
 from impyute.ops.util import toy_df,insert_na
 from impyute.cs.random import random_impute
 from impyute.cs.buck_iterative import buck_iterative
+from impyute.ts.moving_window import moving_window
 from missingpy import MissForest
 
 #use pip to install fancyimpute
@@ -64,6 +65,7 @@ def nafiller():
                     the same row or column.",
         'FillRef': "Impute missing values using values from an external \
                     reference dataset.",
+        'MW': "Interpolate the missing values with moving window.",
         'KNN': "Impute missing values using scikit-learn's KNNImputer function. \
                 Note: slow for large datasets.",
         'KNN2': "Impute missing values using KNN2",
@@ -98,6 +100,7 @@ def nafiller():
     FillMax_parser = sub_parsers.add_parser('FillMax', help=commands['FillMax'])
     FillRand_parser = sub_parsers.add_parser('FillRand', help=commands['FillRand'])
     FillRef_parser = sub_parsers.add_parser('FillRef', help=commands['FillRef'])
+    MW_parser = sub_parsers.add_parser('MW', help=commands['MW'])
     KNN_parser = sub_parsers.add_parser('KNN', help=commands['KNN'])
     fKNN_parser = sub_parsers.add_parser('fKNN', help=commands['fKNN'])
     EM_parser = sub_parsers.add_parser('EM', help=commands['EM'])
@@ -116,7 +119,7 @@ def nafiller():
         'output', type=str, metavar='out_df',
         help="Output data frame.")
     DropNA_parser.add_argument(
-        '-a', '--axis', type=int, choices=range(2), default=0,
+        '--axis', type=int, choices=range(2), default=0,
         help="0 : drop rows with any missing values, 1 : drop columns with \
             missing values. Default: 0")
     DropNA_parser.add_argument(
@@ -130,7 +133,7 @@ def nafiller():
         'output', type=str, metavar='out_df',
         help="Output data frame.")
     FillValue_parser.add_argument(
-        '-s', '--score', type=float, default=0.0,
+        '--score', type=float, default=0.0,
         help="The value uesd to fill all NAs.")
     FillValue_parser.add_argument(
         '--decimal', type=int, default=5,
@@ -143,7 +146,7 @@ def nafiller():
         'output', type=str, metavar='out_df',
         help="Output data frame.")
     FillMean_parser.add_argument(
-        '-a', '--axis', type=int, choices=range(2), default=1,
+        '--axis', type=int, choices=range(2), default=1,
         help="0 means column, 1 means row. Default: fill NAs with row means")
     FillMean_parser.add_argument(
         '--decimal', type=int, default=5,
@@ -156,7 +159,7 @@ def nafiller():
         'output', type=str, metavar='out_df',
         help="Output data frame.")
     FillMedian_parser.add_argument(
-        '-a', '--axis', type=int, choices=range(2), default=1,
+        '--axis', type=int, choices=range(2), default=1,
         help="0 means column, 1 means row. Default: fill NAs with row medians")
     FillMedian_parser.add_argument(
         '--decimal', type=int, default=5,
@@ -169,7 +172,7 @@ def nafiller():
         'output', type=str, metavar='out_df',
         help="Output data frame.")
     FillMin_parser.add_argument(
-        '-a', '--axis', type=int, choices=range(2), default=1,
+        '--axis', type=int, choices=range(2), default=1,
         help="0 means column, 1 means row. Default: fill NAs with the minimum value of the rows.")
     FillMin_parser.add_argument(
         '--decimal', type=int, default=5,
@@ -182,7 +185,7 @@ def nafiller():
         'output', type=str, metavar='out_df',
         help="Output data frame.")
     FillMax_parser.add_argument(
-        '-a', '--axis', type=int, choices=range(2), default=1,
+        '--axis', type=int, choices=range(2), default=1,
         help="0 means column, 1 means row. Default: fill NAs with the maximum value of the rows.")
     FillMax_parser.add_argument(
         '--decimal', type=int, default=5,
@@ -195,7 +198,7 @@ def nafiller():
         'output', type=str, metavar='out_df',
         help="Output data frame.")
     FillRand_parser.add_argument(
-        '-a', '--axis', type=int, choices=range(2), default=1,
+        '--axis', type=int, choices=range(2), default=1,
         help="0 means column, 1 means row. Default: fill NAs with values randomly selected from rows.")
     FillRand_parser.add_argument(
         '--decimal', type=int, default=5,
@@ -208,12 +211,50 @@ def nafiller():
         'output', type=str, metavar='out_df',
         help="Output data frame.")
     FillRef_parser.add_argument(
-        '-r', '--ref', type=str,
+        '--ref', type=str,
         help="File name of the external reference.")
     FillRef_parser.add_argument(
         '--decimal', type=int, default=5,
         help="Number of decimal places to round each column to. default: %(default)s")
 
+    MW_parser.add_argument(
+        'input', type=str, metavar='input_df',
+        help="Input data frame.")
+    MW_parser.add_argument(
+        'output', type=str, metavar='out_df',
+        help="Output data frame.")
+    MW_parser.add_argument(
+        '--nindex', type=int, choices=[0, -1, None],
+        default=None,
+        help="Null index. Index of the null value inside the moving average window. \
+            See impyute documentation for details. default: %(default)s")
+    MW_parser.add_argument(
+        '--wsize', type=int, default=5,
+        help="Size of the moving average window/area of values being used \
+            for each local imputation. This number includes the missing value. \
+            default: %(default)s")
+    MW_parser.add_argument(
+        '--errors', type=str, choices=["raise", "coerce", "ignore"], 
+        default='coerce',
+        help="Errors will occur with the indexing of the windows - for \
+            example if there is a nan at data[x][0] and `nindex` is set to \
+            -1 or there is a nan at data[x][-1] and `nindex` is set to 0. `\
+            'raise' will raise an error, `coerce` will try again using an \
+            nindex set to the middle and `ignore` will just leave it as a \
+            nan  default: %(default)s")
+    MW_parser.add_argument(
+        '--func', type=str, choices=["mean", "median"], 
+        default='mean',
+        help="Function to summerzie values within the moving window. \
+            default: %(default)s")
+    MW_parser.add_argument(
+        '--axis', type=int, choices=range(2), default=1,
+        help="0 means column, 1 means row. Default: fill missing value \
+            with windows moving on rows.")
+    MW_parser.add_argument(
+        '--decimal', type=int, default=5,
+        help="Number of decimal places to round each column to. default: %(default)s")
+    
     KNN_parser.add_argument(
         'input', type=str, metavar='input_df',
         help="Input data frame.")
@@ -306,20 +347,28 @@ def nafiller():
         'output', type=str, metavar='out_df',
         help="Name of the output data frame.")
     ToyDf_parser.add_argument(
-        '-r', '--nrow', type=int, default=10,
+        '--nrow', type=int, default=10,
         help="Number of rows. default: %(default)s")
     ToyDf_parser.add_argument(
-        '-c', '--ncol', type=int, default=10,
+        '--ncol', type=int, default=10,
         help="Number of columns. default: %(default)s")
     ToyDf_parser.add_argument(
-        '--na', type=int, default=5,
+        '--nmiss', type=float, default=5,
         help="Number of missing values ingested into the dataframe. default: %(default)s")
     ToyDf_parser.add_argument(
-        '-s', '--seed', type=int, default=123,
+        '--seed', type=int, default=123,
         help="Seed used to initialize a pseudorandom number generator. default: %(default)s")
     ToyDf_parser.add_argument(
         '--prefix', type=str, default='s',
-        help="Prefix of the column names, a series numbers will be appended to the prefix. default: %(default)s")
+        help="Prefix of the column names, a series numbers will be appended to \
+            the prefix. If this is set to None, as np.ndarray rather than pd.dataframe \
+            will be returned. default: %(default)s")
+    ToyDf_parser.add_argument(
+        '--min', type=float, default=0.0, 
+        help="The minimum value. default: %(default)s")
+    ToyDf_parser.add_argument(
+        '--max', type=float, default=1.0, 
+        help="The maximum value. default: %(default)s")
     ToyDf_parser.add_argument(
         '--decimal', type=int, default=5,
         help="Number of decimal places to round each column to. default: %(default)s")
@@ -331,10 +380,10 @@ def nafiller():
         'output', type=str, metavar='out_df',
         help="Output data frame.")
     InsertNA_parser.add_argument(
-        '--na', type=int,
+        '--nmiss', type=int,
         help="Number of missing values ingested into the dataframe.")
     InsertNA_parser.add_argument(
-        '-s', '--seed', type=int, default=123,
+        '--seed', type=int, default=123,
         help="Seed used to initialize a pseudorandom number generator. default: %(default)s")
     InsertNA_parser.add_argument(
         '--decimal', type=int, default=5,
@@ -483,6 +532,25 @@ def nafiller():
                     continue
             output_df = input_df
             output_df = output_df.round(args.decimal)
+            output_df.to_csv(args.output, sep="\t", na_rep="NaN")
+            logging.info("File \"%s\" contains %d missing values ..." %
+                        (args.output, output_df.isna().sum().sum()))
+        elif command.lower() == 'mw':
+            input_df = read_df(args.input)
+            logging.info("File \"%s\" contains %d missing values ..." %
+                        (args.input, input_df.isna().sum().sum()))
+            logging.info("Replace missing values using moving window on %s ..." % axis_name[args.axis])
+            if args.axis == 1:
+                output_df = moving_window(
+                    input_df, nindex = args.nindex, wsize=args.wsize, 
+                    errors=args.errors, func=getattr(np, args.func))
+                output_df = output_df.round(args.decimal)
+            elif args.axis == 0:
+                output_df = moving_window(
+                    input_df.T, nindex = args.nindex, wsize=args.wsize, 
+                    errors=args.errors, func=getattr(np, args.func))
+                output_df = output_df.round(args.decimal).T
+           
             output_df.to_csv(args.output, sep="\t", na_rep="NaN")
             logging.info("File \"%s\" contains %d missing values ..." %
                         (args.output, output_df.isna().sum().sum()))
@@ -576,9 +644,10 @@ def nafiller():
 
         elif command.lower() == 'toydf':
             logging.info("Generate toy dataframe ...")
-            output_df = toy_df(nrow = args.nrow, ncol = args.ncol, 
-                               n_miss = args.na, sample_prefix=args.prefix,
-                               seed=args.seed)
+            output_df = toy_df(n_rows = args.nrow, n_cols = args.ncol, 
+                               missingness = args.nmiss, sample_prefix=args.prefix,
+                               min_val = args.min, max_val = args.max, 
+                               rand_seed=args.seed)
             #print(output_df)
             output_df = output_df.round(args.decimal)
             output_df.to_csv(args.output, sep="\t", na_rep="NaN")
@@ -589,7 +658,7 @@ def nafiller():
             logging.info("File \"%s\" contains %d missing values ..." %
                          (args.input, input_df.isna().sum().sum()))
             logging.info("Insert %d NAs into dataframe ..." % args.na)
-            output_df = insert_na(df=input_df, n_miss=args.na, seed=args.seed)
+            output_df = insert_na(df=input_df, n_miss=args.nmiss, seed=args.seed)
             output_df = output_df.round(args.decimal)
             output_df.to_csv(args.output, sep="\t", na_rep="NaN")
             logging.info("File \"%s\" contains %d missing values ..." %

{cpgtools-2.0.2.dist-info → cpgtools-2.0.3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: cpgtools
-Version: 2.0.2
+Version: 2.0.3
 Summary: Tools to analyze and visualize DNA methylation data
 Author-email: Liguo Wang <wangliguo78@gmail.com>
 Maintainer-email: Liguo Wang <wangliguo78@gmail.com>

{cpgtools-2.0.2.dist-info → cpgtools-2.0.3.dist-info}/RECORD

@@ -10,37 +10,56 @@ cpgmodule/methylClock.py,sha256=HyMk3vpVwR3yrkLCPv9fVJs6JCeSchbJEBe7i69jdSs,1202
 cpgmodule/padjust.py,sha256=mvbQ9_crn_S39yvWrv_JPoU5OxZGHaw7cV3deBxTPdk,2389
 cpgmodule/region2gene.py,sha256=iuSYa2-ki-qbL1TqqAlTXGT7g-j1uNIA1y7hzMwVM2U,5347
 cpgmodule/utils.py,sha256=NgKT3aJlRT5pQKKO3_e0WB2_u93pY13F-k-r0pvgKno,16095
+cpgmodule/data/AltumAge_cpg.pkl,sha256=T0pfBWrzQO00-z85QNE2CP0ntU0mtF2WkZeEPiArqTw,264691
+cpgmodule/data/AltumAge_multi_platform_cpgs.pkl,sha256=Bo7ZG6AuxXUmLH6dCFfrlYkiTkeLjyqRgcD7yw4mNZ0,264816
+cpgmodule/data/AltumAge_scaler.pkl,sha256=aDMcC4l0wZJGDi6_MeSpdNoykndfgsUtVKEd6mKf9T0,325509
+cpgmodule/data/GA_Bohlin.pkl,sha256=W72ra6APUZDNPmVJ-kRuaVzpiKGgI_K7nDqSFx3nf3w,2667
+cpgmodule/data/GA_Haftorn.pkl,sha256=ZFCJ2h0DWEaa-pHKdsSuWbQGL1JMwDXBtDyhx9DlZLc,4622
+cpgmodule/data/GA_Knight.pkl,sha256=dsKeIt7PxCcw_tcVObtVKB3KqtF7bPH-vQqbClWI5Tc,25322
+cpgmodule/data/GA_Lee_CPC.pkl,sha256=WfeI1bGnIS5_AIX7qnspyGYUgzGOAJ9JJ9CGQjLgkFo,25373
+cpgmodule/data/GA_Lee_RPC.pkl,sha256=rLhr-sboWqIZ6Y08zODh7bgwXBa4SNkE4ZZaIyQTaYc,25382
+cpgmodule/data/GA_Lee_refined_RPC.pkl,sha256=bXiZIgFSoX7Sr0ai1zHzGXv-EMGBglvx8z5vr3IpccA,25348
+cpgmodule/data/GA_Mayne.pkl,sha256=CUfwiVIywJZwTb0PhRuW-6TQ5H1kO7tR6KHepyzBULg,1899
+cpgmodule/data/Hannum.pkl,sha256=gXJxy6S8lBCUdr_T7ZM3R6hqKI22yev5-2giCPCCdLc,2049
+cpgmodule/data/Horvath_2013.pkl,sha256=qwP614VYmmaESKanQ680sYgaHSWJrP73im_f5duzKgU,8313
+cpgmodule/data/Horvath_2018.pkl,sha256=IQcFNIg-z-Mrq8vEoHI509c64Dt1wtyHInU9YwsYP-w,9225
+cpgmodule/data/Levine.pkl,sha256=OhasOuEAvbDblZfGGFmu82kDqdo5CQ2DjZ8hfCofhvI,11751
+cpgmodule/data/Lu_DNAmTL.pkl,sha256=SdjT9x8A0GbnKoMlDhgslmmINJ8e5Asyk9KQlw_EtJo,3548
+cpgmodule/data/Ped_McEwen.pkl,sha256=-hxOAqFUxORmPLV_FKYZxjOFtabxPzbbzfY6JTitq8k,2654
+cpgmodule/data/Ped_Wu.pkl,sha256=gjXtpdpQ8QVJs1I6UM-VPAvQjNd-JDoy5DzDL-gP-Cg,2924
+cpgmodule/data/Zhang_BLUP.pkl,sha256=dpH0L3qTxMAJ50XtTeNMmqx1khZkZyrH204E37fE37E,7038226
+cpgmodule/data/Zhang_EN.pkl,sha256=RFEOmBQGXZvIwQ7tOYT8itOPU87V2Y02vJA2PfY6TnI,11844
 cpgmodule/data/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-cpgtools-2.0.2.data/scripts/CpG_aggregation.py,sha256=iSSUanCPlTkT3f6Df_f_b6zEP2Ixzse9zFwJLL5z2Qw,7278
-cpgtools-2.0.2.data/scripts/CpG_anno_position.py,sha256=j8l4v7SpGFaJ3pBVE5qK8coMkxe5h4p1bwmhcPnhxMk,4643
-cpgtools-2.0.2.data/scripts/CpG_anno_probe.py,sha256=bACac7x9zX2E1QJnUUmNKS6YNKg_f4K-jxwl_v93--4,3171
-cpgtools-2.0.2.data/scripts/CpG_density_gene_centered.py,sha256=JM2PrvHCnGAvymBbbIBr30AfXwu69WgJkJNy6PCmCrg,5266
-cpgtools-2.0.2.data/scripts/CpG_distrb_chrom.py,sha256=q3xZ1AH4JEif1DQRG6UXiiUb4jZyt2khzTZld1jaXnA,6207
-cpgtools-2.0.2.data/scripts/CpG_distrb_gene_centered.py,sha256=tLfalDRzklBcNfZxhABjhprcBlk4HgUyxXxznOGVTN8,7736
-cpgtools-2.0.2.data/scripts/CpG_distrb_region.py,sha256=nJGgZLhZe2kYCPnxuW--EemxOcoReu2hdkIAgl-7UAE,5391
-cpgtools-2.0.2.data/scripts/CpG_logo.py,sha256=U8RxYPmakKii1xmEgG22tKfdZBPpjhZbAfKxgF_Z-O8,4597
-cpgtools-2.0.2.data/scripts/CpG_to_gene.py,sha256=fciNtI5N6fO-jZX2eyKgiAhDIsus4SljYSCbEQMeTHI,6114
-cpgtools-2.0.2.data/scripts/beta_PCA.py,sha256=cRlqGC5CQlpsmzhAwy2AoI4_lLwjFh_rvn7ObNbHgYg,7155
-cpgtools-2.0.2.data/scripts/beta_UMAP.py,sha256=SJfxtCsM1NTK5rYnZjtXiDj_x1kJiYZvR1NGHKo0IRI,8079
-cpgtools-2.0.2.data/scripts/beta_imputation.py,sha256=o7wM_iHFwhxjRAMQ5_fCxgAfO9VYe48O9dY4BeZF2wA,28928
-cpgtools-2.0.2.data/scripts/beta_jitter_plot.py,sha256=Knja1n1rpD0qe3FHkNPax0p6BYsmAtEQBFB1wBdpHyY,4389
-cpgtools-2.0.2.data/scripts/beta_m_conversion.py,sha256=992tJI0IzkphUaEr_9_CveSRPjKdnyYkCTO10D_xkbg,2848
-cpgtools-2.0.2.data/scripts/beta_profile_gene_centered.py,sha256=Jb9mm8y-1cKH_EepRFhUH5mfBdoAt0zpN_VXETRnQek,7312
-cpgtools-2.0.2.data/scripts/beta_profile_region.py,sha256=GHDPyUFR9XJm2CK0_9wCKossMTWWvn4VwYCCSA8kn2E,5971
-cpgtools-2.0.2.data/scripts/beta_selectNBest.py,sha256=Uu_MvQUm6Zc8MGKuGUEooJ-IL7C1eg_LNRqQsNdLaWs,4638
-cpgtools-2.0.2.data/scripts/beta_stacked_barplot.py,sha256=2fcypD_BE4XqK-vl8hHsgyWqvp3I9oLvg8tF2dd5QZ0,3415
-cpgtools-2.0.2.data/scripts/beta_stats.py,sha256=WBh3Aquk_AHeUcteLPtt2Q2yKpqu5aBA38zaFz_7mVI,3021
-cpgtools-2.0.2.data/scripts/beta_tSNE.py,sha256=0UTxNxyaDb-iNqbeIfFKj9DRURTQcHeJdltr-iY72XM,8450
-cpgtools-2.0.2.data/scripts/beta_topN.py,sha256=gmbmJZoGJt3QljlRHUA8LaKSIurdCNgtn2J9LAIQNCo,3914
-cpgtools-2.0.2.data/scripts/beta_trichotmize.py,sha256=T594UfSCDJHRFyGvov7qetLQs10WU73PGVVCDNrwNPg,7143
-cpgtools-2.0.2.data/scripts/dmc_Bayes.py,sha256=imqKv5x8s_plXQPL3_d9OpqSI-imrSfUj-k39Zf1XqA,13735
-cpgtools-2.0.2.data/scripts/dmc_bb.py,sha256=pOEEHT-hT--r6IswZwQFyGri77OJqbW1y9VVG8pzzpg,8407
-cpgtools-2.0.2.data/scripts/dmc_fisher.py,sha256=t18smNJAtipmDm3xgUg62ccKsFQWcdKBo4Tm2cxx43s,5163
-cpgtools-2.0.2.data/scripts/dmc_glm.py,sha256=_vJiZhbGA-Rv5v5oBU9N9lGND8MTEVAFHHFqW5hgfSw,6516
-cpgtools-2.0.2.data/scripts/dmc_logit.py,sha256=V35wyBgcdiUbsR_NDnEDfs6F2yPyz11ryZvYkkV6Ess,8488
-cpgtools-2.0.2.data/scripts/dmc_nonparametric.py,sha256=eFyUy7jXl8bPyySKZLEi3LVxYkDOKp9S4XBXevYvbVw,4945
-cpgtools-2.0.2.data/scripts/dmc_ttest.py,sha256=jOW0el_NeJlBuF91wKN2UHnu7phoP0OPrKCNCaOAQBs,6704
-cpgtools-2.0.2.data/scripts/predict_sex.py,sha256=ojoMJ6XwBsE1kGpxzKGZ4TZPs5JcUwI_C_9ieEQbB9c,4755
+cpgtools-2.0.3.data/scripts/CpG_aggregation.py,sha256=iSSUanCPlTkT3f6Df_f_b6zEP2Ixzse9zFwJLL5z2Qw,7278
+cpgtools-2.0.3.data/scripts/CpG_anno_position.py,sha256=j8l4v7SpGFaJ3pBVE5qK8coMkxe5h4p1bwmhcPnhxMk,4643
+cpgtools-2.0.3.data/scripts/CpG_anno_probe.py,sha256=bACac7x9zX2E1QJnUUmNKS6YNKg_f4K-jxwl_v93--4,3171
+cpgtools-2.0.3.data/scripts/CpG_density_gene_centered.py,sha256=JM2PrvHCnGAvymBbbIBr30AfXwu69WgJkJNy6PCmCrg,5266
+cpgtools-2.0.3.data/scripts/CpG_distrb_chrom.py,sha256=q3xZ1AH4JEif1DQRG6UXiiUb4jZyt2khzTZld1jaXnA,6207
+cpgtools-2.0.3.data/scripts/CpG_distrb_gene_centered.py,sha256=tLfalDRzklBcNfZxhABjhprcBlk4HgUyxXxznOGVTN8,7736
+cpgtools-2.0.3.data/scripts/CpG_distrb_region.py,sha256=nJGgZLhZe2kYCPnxuW--EemxOcoReu2hdkIAgl-7UAE,5391
+cpgtools-2.0.3.data/scripts/CpG_logo.py,sha256=U8RxYPmakKii1xmEgG22tKfdZBPpjhZbAfKxgF_Z-O8,4597
+cpgtools-2.0.3.data/scripts/CpG_to_gene.py,sha256=fciNtI5N6fO-jZX2eyKgiAhDIsus4SljYSCbEQMeTHI,6114
+cpgtools-2.0.3.data/scripts/beta_PCA.py,sha256=cRlqGC5CQlpsmzhAwy2AoI4_lLwjFh_rvn7ObNbHgYg,7155
+cpgtools-2.0.3.data/scripts/beta_UMAP.py,sha256=SJfxtCsM1NTK5rYnZjtXiDj_x1kJiYZvR1NGHKo0IRI,8079
+cpgtools-2.0.3.data/scripts/beta_jitter_plot.py,sha256=Knja1n1rpD0qe3FHkNPax0p6BYsmAtEQBFB1wBdpHyY,4389
+cpgtools-2.0.3.data/scripts/beta_m_conversion.py,sha256=992tJI0IzkphUaEr_9_CveSRPjKdnyYkCTO10D_xkbg,2848
+cpgtools-2.0.3.data/scripts/beta_profile_gene_centered.py,sha256=Jb9mm8y-1cKH_EepRFhUH5mfBdoAt0zpN_VXETRnQek,7312
+cpgtools-2.0.3.data/scripts/beta_profile_region.py,sha256=GHDPyUFR9XJm2CK0_9wCKossMTWWvn4VwYCCSA8kn2E,5971
+cpgtools-2.0.3.data/scripts/beta_selectNBest.py,sha256=Uu_MvQUm6Zc8MGKuGUEooJ-IL7C1eg_LNRqQsNdLaWs,4638
+cpgtools-2.0.3.data/scripts/beta_stacked_barplot.py,sha256=2fcypD_BE4XqK-vl8hHsgyWqvp3I9oLvg8tF2dd5QZ0,3415
+cpgtools-2.0.3.data/scripts/beta_stats.py,sha256=WBh3Aquk_AHeUcteLPtt2Q2yKpqu5aBA38zaFz_7mVI,3021
+cpgtools-2.0.3.data/scripts/beta_tSNE.py,sha256=0UTxNxyaDb-iNqbeIfFKj9DRURTQcHeJdltr-iY72XM,8450
+cpgtools-2.0.3.data/scripts/beta_topN.py,sha256=gmbmJZoGJt3QljlRHUA8LaKSIurdCNgtn2J9LAIQNCo,3914
+cpgtools-2.0.3.data/scripts/beta_trichotmize.py,sha256=T594UfSCDJHRFyGvov7qetLQs10WU73PGVVCDNrwNPg,7143
+cpgtools-2.0.3.data/scripts/dmc_Bayes.py,sha256=imqKv5x8s_plXQPL3_d9OpqSI-imrSfUj-k39Zf1XqA,13735
+cpgtools-2.0.3.data/scripts/dmc_bb.py,sha256=pOEEHT-hT--r6IswZwQFyGri77OJqbW1y9VVG8pzzpg,8407
+cpgtools-2.0.3.data/scripts/dmc_fisher.py,sha256=t18smNJAtipmDm3xgUg62ccKsFQWcdKBo4Tm2cxx43s,5163
+cpgtools-2.0.3.data/scripts/dmc_glm.py,sha256=_vJiZhbGA-Rv5v5oBU9N9lGND8MTEVAFHHFqW5hgfSw,6516
+cpgtools-2.0.3.data/scripts/dmc_logit.py,sha256=V35wyBgcdiUbsR_NDnEDfs6F2yPyz11ryZvYkkV6Ess,8488
+cpgtools-2.0.3.data/scripts/dmc_nonparametric.py,sha256=eFyUy7jXl8bPyySKZLEi3LVxYkDOKp9S4XBXevYvbVw,4945
+cpgtools-2.0.3.data/scripts/dmc_ttest.py,sha256=DDmWi1udo1gqOAQvFTeRxhIJuAgEmakSNU7P4LKTT7U,6786
+cpgtools-2.0.3.data/scripts/predict_missing.py,sha256=pNSfOD9i7LNLG9BGa80W2-bsCi6qcUlIwoiLnBLbPlo,32465
+cpgtools-2.0.3.data/scripts/predict_sex.py,sha256=ojoMJ6XwBsE1kGpxzKGZ4TZPs5JcUwI_C_9ieEQbB9c,4755
 impyute/__init__.py,sha256=Q07nw2fDjLm_c3EQWMpSo8nZCfC-fvs2lpRG5uha-gg,87
 impyute/contrib/__init__.py,sha256=DgGgN0iBoMfHjzr9edz-ZgtJ2KeyIDlyV1t8hxhcM2c,209
 impyute/contrib/compare.py,sha256=psWygE7PD4Cky4MoTJLAgjaEkTXwqemv3NTKkKVaapo,2852
@@ -62,7 +81,7 @@ impyute/ops/error.py,sha256=lyXJcIDyfdrj_JJbsEI18z-t4UKi1mpLTyt3iS2YvTs,226
 impyute/ops/inverse_distance_weighting.py,sha256=88hmyc-dWltP66MbjrW-VHBcVgPOI0V0BkrV30B-Lyc,1017
 impyute/ops/matrix.py,sha256=-eniwqvbvwXNrYw8PmIMD95uMcPMq6HE6OBOyjzR-Vk,837
 impyute/ops/testing.py,sha256=3ZRVL1sc5IIQLPW2GrD6-lF4_nVnSLo7SBW4rfaOMLA,415
-impyute/ops/util.py,sha256=Tcm8reCrWQf8btKRP5StawBL1UV_GOBWmzy1NYDcPbY,2204
+impyute/ops/util.py,sha256=167Xpwib86kT09-pZnJg-VhyVD9r-z7Gkd_L42A2-EY,2838
 impyute/ops/wrapper.py,sha256=bQj3r9WsZxqNw51y3OobyyXPPxCeISUv2jb-Ga2C_-M,6022
 impyute/ts/__init__.py,sha256=veePCYSBfo1t5Ahh3wrVCNveizcniXZYhjyS7ahkIhI,145
 impyute/ts/locf.py,sha256=qusLWfBrepKzFIkeGxIS0S5KnqRgZde2CV6mcF5nf4c,1876
@@ -75,8 +94,8 @@ missingpy/utils.py,sha256=sMU4OGHPvRgReT8e_HqGCYvjAJZkE_qlAPDzLo-_M6U,4360
 missingpy/tests/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 missingpy/tests/test_knnimpute.py,sha256=rR1OPZ4-IzcIKgWmSEN7UEPvVSRwJe0KU_wTxPr46k0,17527
 missingpy/tests/test_missforest.py,sha256=5YfKZf_xdy9RcXmnlFz7cJDqdnspJDzzrxLnVVWJi3A,13725
-cpgtools-2.0.2.dist-info/LICENSE,sha256=NAIE1kmjlmRNJ1BwR9m9i0jXHmQqqujTnEyIBuIxvwM,1074
-cpgtools-2.0.2.dist-info/METADATA,sha256=EfdjaKSMi75Wo041GCIx9gd9JjFf7rULeCkAhw2uuqY,2943
-cpgtools-2.0.2.dist-info/WHEEL,sha256=GV9aMThwP_4oNCtvEC2ec3qUYutgWeAzklro_0m4WJQ,91
-cpgtools-2.0.2.dist-info/top_level.txt,sha256=L6IX1ORvZ1JssvdU8qOtU99-vbMK9ZSIgYg4zH-rL5Y,28
-cpgtools-2.0.2.dist-info/RECORD,,
+cpgtools-2.0.3.dist-info/LICENSE,sha256=NAIE1kmjlmRNJ1BwR9m9i0jXHmQqqujTnEyIBuIxvwM,1074
+cpgtools-2.0.3.dist-info/METADATA,sha256=N1FqwvSLFmK2DvVyYY4oHcqbo6Vj1B4ii48vESlNPkU,2943
+cpgtools-2.0.3.dist-info/WHEEL,sha256=R06PA3UVYHThwHvxuRWMqaGcr-PuniXahwjmQRFMEkY,91
+cpgtools-2.0.3.dist-info/top_level.txt,sha256=L6IX1ORvZ1JssvdU8qOtU99-vbMK9ZSIgYg4zH-rL5Y,28
+cpgtools-2.0.3.dist-info/RECORD,,

{cpgtools-2.0.2.dist-info → cpgtools-2.0.3.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (75.1.0)
+Generator: setuptools (75.5.0)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

impyute/ops/util.py

@@ -41,20 +41,40 @@ def execute_fn_with_args_and_or_kwargs(fn, args, kwargs):
     except TypeError:
         return fn(*args)
 
-def toy_df(nrow, ncol, n_miss, sample_prefix, seed):
-    """
-    Make a dataFrame (nrow x ncol) with random values between 0 and 1, add
-    some missing values (n_miss). Generate a toy dataframe for testing purposes.
-    """
-    np.random.seed(seed)
-    data = np.random.rand(nrow*ncol).reshape((nrow, ncol)).astype(float)
-    x_ind = np.random.choice(nrow, n_miss)
-    y_ind = np.random.choice(ncol, n_miss)
-    for x,y in zip(x_ind, y_ind):
-        data[x][y] =  np.nan
-    colNames = [sample_prefix + '_' + str(i) for i in range(0,ncol)]
-    df = pd.DataFrame(data, columns=colNames)
-    return df
+def toy_df(n_rows=20, n_cols=5, missingness=0.2, min_val=0, max_val=1,
+              missing_value=np.nan, rand_seed=1234, sample_prefix=None):
+    """Generate an array or DataFrame with NaNs"""
+    np.random.seed(rand_seed)
+    X = np.random.uniform(
+        low = min_val, high = max_val, size = n_rows * n_cols).reshape(n_rows, n_cols).astype(
+        float)
+    # check missingness
+    if missingness > 0:
+        # If missingness >= 1 then use it as approximate (see below) count
+        if missingness >= 1:
+            n_missing = int(missingness)
+        else:
+            n_missing = int(missingness * n_rows * n_cols)
+            print(n_missing)
+    
+    # Introduce NaNs until n_miss "NAs" are inserted.
+    missing_count = 0
+    for i,j in zip(np.random.choice(n_rows, n_missing), np.random.choice(n_cols, n_missing)):
+        if np.isnan(X[i][j]):
+            continue
+        else:
+            X[i][j] = missing_value
+            missing_count += 1
+        if missing_count >= n_missing:
+            break
+
+    # check sample_prefix
+    if sample_prefix is None:
+        return X
+    else:
+        colNames = [sample_prefix + '_' + str(i) for i in range(0, n_cols)]
+        return pd.DataFrame(X, columns=colNames)
+    
 
 def insert_na(df, n_miss, seed):
     np.random.seed(seed)