cpgtools 2.0.5__py3-none-any.whl

cpgtools-2.0.5.data/scripts/predict_sex.py

@@ -0,0 +1,126 @@
+#!python
+
+"""
+#==============================================================================
+Predict sex based on the semi-methylation (also known as genomic imprinting) 
+ratio. This method leverages the fact that, due to X chromosome inactivation,
+females have a higher proportion of semi-methylated CpGs on their X chromosomes.
+A log2(ratio) greater than 0 indicates a female, while a log2(ratio) less than
+0 indicates a male.
+
+Example of input data file
+---------------------------
+CpG_ID    Sample_01    Sample_02    Sample_03    Sample_04
+cg_001    0.831035    0.878022    0.794427    0.880911
+cg_002    0.249544    0.209949    0.234294    0.236680
+cg_003    0.845065    0.843957    0.840184    0.824286
+
+Example of output file
+----------------------
+Sample_ID    log2_SM_ratio    Predicted_sex
+Sample_01    -2.249628052954919      Male
+Sample_02    -2.2671726671830674     Male
+Sample_03    1.4530581933290616      Female
+Sample_04    1.4808015115356654      Female
+
+...
+
+"""
+import sys
+import numpy as np
+from optparse import OptionParser
+from cpgmodule.utils import printlog
+from cpgmodule import ireader
+import pandas as pd
+from cpgmodule._version import __version__
+
+__author__ = "Liguo Wang"
+__copyright__ = "Copyleft"
+__credits__ = []
+__license__ = "GPL"
+__maintainer__ = "Liguo Wang"
+__email__ = "wang.liguo@mayo.edu"
+__status__ = "Development"
+
+    
+def main():
+    
+    usage="%prog [options]" + "\n"
+    parser = OptionParser(usage,version="%prog " + __version__)
+    parser.add_option("-i","--input_file",action="store", type="string",dest="input_file", help="Tab-separated data frame file containing beta values with the 1st row containing sample IDs and the 1st column containing CpG IDs.")
+    parser.add_option("-x","--xprobe",action="store", type="string",dest="xprobe_file", help="File with CpG IDs mapped to the X chromosome, with one probe listed per row.")
+    parser.add_option("-c","--cut",action="store", type='float', dest="cutoff", default=0.0, help="The cutoff of log2(SM ratio) to determine the sex prediction. Log2(SM ratio) greater than this cutoff indicates a female, while a log2(ratio) less than this cutoff indicates a male. default=%default")
+    parser.add_option("-o","--output",action="store", type='string', dest="out_file", help="The prefix of the output file.")
+    (options,args)=parser.parse_args()
+    
+    print ()
+    if not (options.input_file):
+        print (__doc__)
+        parser.print_help()
+        sys.exit(101)
+    if not (options.xprobe_file):
+        print (__doc__)
+        parser.print_help()
+        sys.exit(102)    
+    if not (options.out_file):
+        print (__doc__)
+        parser.print_help()
+        sys.exit(103)    
+    
+    printlog("Reading X probes from: \"%s\"" % (options.xprobe_file))
+    x_cpgs = set()
+    for l in ireader.reader(options.xprobe_file):
+        l = l.strip()
+        if l.startswith('#'):
+            continue
+        x_cpgs.add(l)
+    printlog("Total %d X probes loaded." % len(x_cpgs))
+    
+    printlog("Reading input file: \"%s\"" % (options.input_file))
+    df1 = pd.read_csv(options.input_file, index_col = 0, sep="\t")
+    #print (df1)
+    
+    #remove any rows with NAs
+    df2 = df1.dropna(axis=0, how='any')
+    printlog("%d CpGs with missing values were removed." % (len(df1) - len(df2)))
+    #print (df2)
+    
+    sample_cpg_ids = df2.index
+    sample_names = df2.columns
+    found_x_cpgs = list(x_cpgs & set(sample_cpg_ids))
+    printlog("Found %d CpGs located on the chrX from file: %s" % (len(found_x_cpgs), options.input_file))
+    
+    # only X probes in df3
+    df3 = df2.loc[list(found_x_cpgs)]
+    #pd.DataFrame.to_csv(df3, options.out_file + '.tmp.tsv', sep="\t", index_label="sample")
+    
+    low_beta_range = [0, 0.2]
+    mid_beta_range = [0.3, 0.7]
+    high_beta_range = [0.8, 1.0]
+    
+    output = {}
+    for s in sample_names:
+        output[s] = {}
+        low_beta_count = pd.cut(df3[s], low_beta_range).count()
+        mid_beta_count = pd.cut(df3[s], mid_beta_range).count()
+        high_beta_count = pd.cut(df3[s], high_beta_range).count()
+        try:
+            ratio = np.log2(mid_beta_count/(low_beta_count + high_beta_count))
+        except:
+           ratio = np.nan
+        output[s]['log2_SM_ratio'] = ratio
+        
+        if ratio > options.cutoff:
+            output[s]['Predicted_sex'] = 'Female'
+        elif ratio < options.cutoff:
+            output[s]['Predicted_sex'] = 'Male'
+        else:
+            output[s]['Predicted_sex'] = 'Unknown'
+    df_out = pd.DataFrame(output).T
+    
+    outfile = options.out_file + '.predicted_sex.tsv'
+    printlog("Writing to file: \"%s\"" % outfile)
+    pd.DataFrame.to_csv(df_out, outfile, sep="\t", index_label="Sample_ID")
+
+if __name__=='__main__':
+    main()    

cpgtools-2.0.5.dist-info/METADATA

@@ -0,0 +1,59 @@
+Metadata-Version: 2.4
+Name: cpgtools
+Version: 2.0.5
+Summary: Tools to analyze and visualize DNA methylation data
+Author-email: Liguo Wang <wangliguo78@gmail.com>
+Maintainer-email: Liguo Wang <wangliguo78@gmail.com>
+License-Expression: MIT
+Project-URL: Documentation, https://cpgtools.readthedocs.io/en/latest/index.html
+Project-URL: Repository, https://github.com/liguowang/cpgtools.git
+Keywords: DNA methylation,EPIC,450K,850K,935K,RRBS,WGBS
+Classifier: Programming Language :: Python :: 3
+Classifier: Development Status :: 4 - Beta
+Classifier: Environment :: Console
+Classifier: Intended Audience :: Science/Research
+Classifier: Operating System :: MacOS :: MacOS X
+Classifier: Operating System :: POSIX
+Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
+Requires-Python: >=3.5
+Description-Content-Type: text/markdown
+License-File: LICENSE.txt
+Requires-Dist: numpy
+Requires-Dist: scipy
+Requires-Dist: scikit-learn
+Requires-Dist: weblogo
+Requires-Dist: bx-python
+Requires-Dist: pandas
+Requires-Dist: umap-learn
+Requires-Dist: fancyimpute
+Requires-Dist: pycombat
+Requires-Dist: matplotlib
+Dynamic: license-file
+
+## Install CpGtools using [pip](https://pip.pypa.io/en/stable/)
+
+1. (Optional) Create Virtual Environments (Note: `venv` is available in Python 3.3 and later. You can also use [virtualenv](https://packaging.python.org/en/latest/key_projects/#virtualenv))
+
+ `$ python3 -m venv my_env` (will create a directory called my_env)
+ 
+ `$ source my_env/bin/activate`
+
+2. Install CpGtools
+
+ `$ pip install cpgtools`
+ 
+ or
+ 
+ `$ pip install git+https://github.com/liguowang/cpgtools.git`
+
+3. Upgrade
+
+ `$ pip install cpgtools --upgrade`
+
+4. Uninstall
+
+ `pip -y uninstall cpgtools`
+
+## Documentation
+
+https://cpgtools.readthedocs.io/en/latest/

cpgtools-2.0.5.dist-info/RECORD

@@ -0,0 +1,104 @@
+impyutelib.py,sha256=cEHb_sKSapIOKubN2estkV5NcAPFENeYwzgeykT24a0,30719
+misspylib.py,sha256=3r-UN1bgKz123KMDrya1nPSEYzrI1Ef0MvyAe4WoqPU,24864
+cpgmodule/BED.py,sha256=ZNAhGZPFMFD4UpVwGTDOM0hMLnfXF52zerdMb21sH6s,12675
+cpgmodule/MI.py,sha256=pkUWzKXYeyRuGsGKZdFVxHzFWikkuJavdQ_4fsnN3U4,8649
+cpgmodule/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+cpgmodule/_version.py,sha256=xEb7Z4b8xalXXExBg42XPAhbJKniHzcsEPjp-6S3ppg,22
+cpgmodule/cgID.py,sha256=DLG5Djm6JP0d6MiFvP_keUXv_rYxESWrISuVClTs8kw,16017914
+cpgmodule/extend_bed.py,sha256=sjRxbRJFRumjYHwd6_AMTAYBG29yXQPYp1lDjTv2Q_Q,4648
+cpgmodule/imotif.py,sha256=j7_MQFnowGsVTGCRQHHLUnEzSD0HehZPEHKKZ68Jv24,9227
+cpgmodule/ireader.py,sha256=NRTdFnQvd1AEkYchfgvTVTixBVwUjn8xNyswc0OWU1Q,720
+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-2.0.5.data/scripts/CpG_aggregation.py,sha256=iSSUanCPlTkT3f6Df_f_b6zEP2Ixzse9zFwJLL5z2Qw,7278
+cpgtools-2.0.5.data/scripts/CpG_anno_position.py,sha256=j8l4v7SpGFaJ3pBVE5qK8coMkxe5h4p1bwmhcPnhxMk,4643
+cpgtools-2.0.5.data/scripts/CpG_anno_probe.py,sha256=bACac7x9zX2E1QJnUUmNKS6YNKg_f4K-jxwl_v93--4,3171
+cpgtools-2.0.5.data/scripts/CpG_density_gene_centered.py,sha256=JM2PrvHCnGAvymBbbIBr30AfXwu69WgJkJNy6PCmCrg,5266
+cpgtools-2.0.5.data/scripts/CpG_distrb_chrom.py,sha256=q3xZ1AH4JEif1DQRG6UXiiUb4jZyt2khzTZld1jaXnA,6207
+cpgtools-2.0.5.data/scripts/CpG_distrb_gene_centered.py,sha256=tLfalDRzklBcNfZxhABjhprcBlk4HgUyxXxznOGVTN8,7736
+cpgtools-2.0.5.data/scripts/CpG_distrb_region.py,sha256=nJGgZLhZe2kYCPnxuW--EemxOcoReu2hdkIAgl-7UAE,5391
+cpgtools-2.0.5.data/scripts/CpG_logo.py,sha256=U8RxYPmakKii1xmEgG22tKfdZBPpjhZbAfKxgF_Z-O8,4597
+cpgtools-2.0.5.data/scripts/CpG_to_gene.py,sha256=fciNtI5N6fO-jZX2eyKgiAhDIsus4SljYSCbEQMeTHI,6114
+cpgtools-2.0.5.data/scripts/beta_PCA.py,sha256=-Cp9vhrNr5nKs6xPLRrQ2NJUj3eTm-kFNvRMv7mKaT4,8487
+cpgtools-2.0.5.data/scripts/beta_UMAP.py,sha256=SJfxtCsM1NTK5rYnZjtXiDj_x1kJiYZvR1NGHKo0IRI,8079
+cpgtools-2.0.5.data/scripts/beta_combat.py,sha256=iX40a_usa_BRPANGvRi8XIIRz_gX8h9-wn3Q7__sT9c,6710
+cpgtools-2.0.5.data/scripts/beta_jitter_plot.py,sha256=Knja1n1rpD0qe3FHkNPax0p6BYsmAtEQBFB1wBdpHyY,4389
+cpgtools-2.0.5.data/scripts/beta_m_conversion.py,sha256=992tJI0IzkphUaEr_9_CveSRPjKdnyYkCTO10D_xkbg,2848
+cpgtools-2.0.5.data/scripts/beta_profile_gene_centered.py,sha256=Jb9mm8y-1cKH_EepRFhUH5mfBdoAt0zpN_VXETRnQek,7312
+cpgtools-2.0.5.data/scripts/beta_profile_region.py,sha256=GHDPyUFR9XJm2CK0_9wCKossMTWWvn4VwYCCSA8kn2E,5971
+cpgtools-2.0.5.data/scripts/beta_selectNBest.py,sha256=Uu_MvQUm6Zc8MGKuGUEooJ-IL7C1eg_LNRqQsNdLaWs,4638
+cpgtools-2.0.5.data/scripts/beta_stacked_barplot.py,sha256=2fcypD_BE4XqK-vl8hHsgyWqvp3I9oLvg8tF2dd5QZ0,3415
+cpgtools-2.0.5.data/scripts/beta_stats.py,sha256=WBh3Aquk_AHeUcteLPtt2Q2yKpqu5aBA38zaFz_7mVI,3021
+cpgtools-2.0.5.data/scripts/beta_tSNE.py,sha256=0UTxNxyaDb-iNqbeIfFKj9DRURTQcHeJdltr-iY72XM,8450
+cpgtools-2.0.5.data/scripts/beta_topN.py,sha256=gmbmJZoGJt3QljlRHUA8LaKSIurdCNgtn2J9LAIQNCo,3914
+cpgtools-2.0.5.data/scripts/beta_trichotmize.py,sha256=T594UfSCDJHRFyGvov7qetLQs10WU73PGVVCDNrwNPg,7143
+cpgtools-2.0.5.data/scripts/dmc_Bayes.py,sha256=imqKv5x8s_plXQPL3_d9OpqSI-imrSfUj-k39Zf1XqA,13735
+cpgtools-2.0.5.data/scripts/dmc_bb.py,sha256=pOEEHT-hT--r6IswZwQFyGri77OJqbW1y9VVG8pzzpg,8407
+cpgtools-2.0.5.data/scripts/dmc_fisher.py,sha256=t18smNJAtipmDm3xgUg62ccKsFQWcdKBo4Tm2cxx43s,5163
+cpgtools-2.0.5.data/scripts/dmc_glm.py,sha256=_vJiZhbGA-Rv5v5oBU9N9lGND8MTEVAFHHFqW5hgfSw,6516
+cpgtools-2.0.5.data/scripts/dmc_logit.py,sha256=V35wyBgcdiUbsR_NDnEDfs6F2yPyz11ryZvYkkV6Ess,8488
+cpgtools-2.0.5.data/scripts/dmc_nonparametric.py,sha256=eFyUy7jXl8bPyySKZLEi3LVxYkDOKp9S4XBXevYvbVw,4945
+cpgtools-2.0.5.data/scripts/dmc_ttest.py,sha256=DDmWi1udo1gqOAQvFTeRxhIJuAgEmakSNU7P4LKTT7U,6786
+cpgtools-2.0.5.data/scripts/predict_missing.py,sha256=pNSfOD9i7LNLG9BGa80W2-bsCi6qcUlIwoiLnBLbPlo,32465
+cpgtools-2.0.5.data/scripts/predict_sex.py,sha256=ojoMJ6XwBsE1kGpxzKGZ4TZPs5JcUwI_C_9ieEQbB9c,4755
+cpgtools-2.0.5.dist-info/licenses/LICENSE.txt,sha256=NAIE1kmjlmRNJ1BwR9m9i0jXHmQqqujTnEyIBuIxvwM,1074
+impyute/__init__.py,sha256=Q07nw2fDjLm_c3EQWMpSo8nZCfC-fvs2lpRG5uha-gg,87
+impyute/contrib/__init__.py,sha256=DgGgN0iBoMfHjzr9edz-ZgtJ2KeyIDlyV1t8hxhcM2c,209
+impyute/contrib/compare.py,sha256=psWygE7PD4Cky4MoTJLAgjaEkTXwqemv3NTKkKVaapo,2852
+impyute/contrib/count_missing.py,sha256=KkCpYeuDP5jRxCcURJbne_k-7Zq1k31oq2aFHpqygx8,742
+impyute/contrib/describe.py,sha256=LI6Xage19-DEEDZVNqaaOjemRAVqVkSlH4mxjjubw-A,2033
+impyute/cs/__init__.py,sha256=ArkuAVHm0z4jl3_UK_FUBF8i2vZUvAZpfVFyryUTm18,373
+impyute/cs/buck_iterative.py,sha256=ceoQ2ij64pXHy7NszErTTRb9h2wctF0CMBexhc6YZSA,3009
+impyute/cs/central_tendency.py,sha256=xHwTVeDL-N-O5refvP536FiVEDODR7s-cgX2Ao9LsfI,2127
+impyute/cs/em.py,sha256=SwvVNMYK3llATR2r1baVCA0hy_fwJIkGD110du9Woos,1631
+impyute/cs/fast_knn.py,sha256=CI4RKMcrbXPi7izUtWo-lnq1BuLYwl8bvbx62dj8Qn0,6246
+impyute/cs/random.py,sha256=-Ti4BwMwUGdsciKTp8OVAgYK6TzGP-R4Nw62UY_xqAs,594
+impyute/dataset/__init__.py,sha256=GK-ktaf86PLZOUlO_oOhvc-55SX1YFLcpjcpgf7a87c,192
+impyute/dataset/base.py,sha256=bNYszhYP62fSeDe8w_Ij4yhEf-dv6NiNGcCdC22OkuY,4445
+impyute/dataset/corrupt.py,sha256=uGCnpofJWfWZYBucQMrwT9yOSpEQAaZSG010Jv6ks1I,1491
+impyute/deletion/__init__.py,sha256=ztemVB8Q6LRaxSv8DDdFzZlGUVUQbsVRA7gvcs_vMhM,124
+impyute/deletion/complete_case.py,sha256=2xBhqNOSmEeW-sBQvl3TVJCcf2Ybmkr8HXNk9xrQ2J0,395
+impyute/ops/__init__.py,sha256=ZP_rQQ0qATGEibUA9I8D1JfD1kRT2Xqw8SsOMPIddog,275
+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=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
+impyute/ts/moving_window.py,sha256=G3Z4ohhqZXAVPflptuOhktwucbW3tg8FySb7gTtBraE,4991
+missingpy/__init__.py,sha256=H_yX0CtfoG2UaJPRcoZKv0AFhi4n-1hHmfIwfqQXoPk,96
+missingpy/knnimpute.py,sha256=WxniKg6-3pvwJa9mipiCZBqkRL_GGHUcxDu-7b57x3k,13456
+missingpy/missforest.py,sha256=UYRf2YANPwxvRPruN3P6xlhJ5JPZB1x8o4xVhYfIp74,24696
+missingpy/pairwise_external.py,sha256=XU_vW-rMCPD3aH9k0UrP_p90QUHDZqe3QZPoOQmu2vo,13221
+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-2.0.5.dist-info/METADATA,sha256=96OWgsyt7bxriebSZX-_6ITD7eaKHcQy0n0p25zS-is,1756
+cpgtools-2.0.5.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+cpgtools-2.0.5.dist-info/top_level.txt,sha256=6kK5IWs15OSnu-SKn2Y6tWI924eoNXNZRIu2xGFLj94,49
+cpgtools-2.0.5.dist-info/RECORD,,

cpgtools-2.0.5.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (80.9.0)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

cpgtools-2.0.5.dist-info/licenses/LICENSE.txt

@@ -0,0 +1,19 @@
+Copyright (c) 2024 The Python Packaging Authority
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

cpgtools-2.0.5.dist-info/top_level.txt

@@ -0,0 +1,5 @@
+cpgmodule
+impyute
+impyutelib
+missingpy
+misspylib

impyute/__init__.py

@@ -0,0 +1,3 @@
+""" Imputations for cross-sectional and time-series data.  """
+
+__all__ = ["cs", "ts"]

impyute/contrib/__init__.py

@@ -0,0 +1,7 @@
+""" Volatile code. Expect stuff in this to change. """
+
+from .describe import describe
+from .count_missing import count_missing
+from .compare import compare
+
+__all__ = ["describe", "count_missing", "compare"]

impyute/contrib/compare.py

@@ -0,0 +1,69 @@
+"""impyute.contrib.compare.py"""
+import importlib
+from sklearn.model_selection import train_test_split
+from sklearn.metrics import accuracy_score
+# pylint: disable=too-many-locals, dangerous-default-value
+
+def compare(imputed, classifiers=["sklearn.svm.SVC"], log_path=None):
+    """
+    Given an imputed dataset with labels and a list of supervised machine
+    learning model, find accuracy score of all model/imputation pairs.
+
+    Parameters
+    ----------
+    imputed: [(str, np.ndarray), (str, np.ndarray)...]
+        List of tuples containing (imputation_name, imputed_data) where
+        `imputation_name` is a string and `imputed_data` is a tuple where
+        `imputed_data`[0] is the data, X and `imputed_data`[1] is the label, y
+    classifiers: [str, str...str] (optional)
+        Provide a list of classifiers to run imputed data sets on. Right now,
+        it ONLY works with sklearn, the format should be like so:
+        `sklearn.SUBMODULE.FUNCTION`. More generally its
+        'MODULE.SUBMODULE.FUNCTION'. If providing a custom classifier, make
+        sure to add the file location to sys.path first and the classifier
+        should also be structured like sklearn (with a `fit` and `predict`
+        method).
+    log_path: str (optional)
+        To write results to a file, provide a relative path
+
+    Returns
+    -------
+    results.txt
+        Classification results on imputed data
+
+    """
+    clfs = []
+    for clf_name in classifiers:
+        mod_name, smod_name, fn_name = clf_name.split(".")
+        try:
+            mod = importlib.import_module("{}.{}".format(mod_name, smod_name))
+            fn = getattr(mod, fn_name)
+            clfs.append([fn_name, fn])
+        except ModuleNotFoundError:
+            print("Cannot import '{}' from '{}.{}'".format(fn_name,
+                                                           mod_name,
+                                                           smod_name))
+
+    results = {imputation_name: [] for imputation_name, _ in imputed}
+
+    for imputation_name, data in imputed:
+        X, y = data
+        X_train, X_test, y_train, y_test = train_test_split(X, y,
+                                                            test_size=0.33,
+                                                            random_state=0)
+        print("Imputation {} =========".format(imputation_name))
+        for clf_name, clf in clfs:
+            clf = clf()
+            clf.fit(X_train, y_train)
+            y_pred = clf.predict(X_test)
+            accuracy = accuracy_score(y_test, y_pred)
+            results[imputation_name].append((clf_name, accuracy))
+            print("...{}".format(clf_name))
+
+    # If not None, write to path
+    if log_path:
+        with open(log_path, 'w') as f:
+            f.write(str(results))
+        print("Results saved to {}".format(log_path))
+
+    return results

impyute/contrib/count_missing.py

@@ -0,0 +1,30 @@
+""" impyute.contrib.count_missing.py """
+import numpy as np
+from impyute.ops import matrix
+
+def count_missing(data):
+    """ Calculate the total percentage of missing values and also the
+    percentage in each column.
+
+    Parameters
+    ----------
+    data: np.array
+        Data to impute.
+
+    Returns
+    -------
+    dict
+        Percentage of missing values in total and in each column.
+
+    """
+    size = len(data.flatten())
+    nan_xy = matrix.nan_indices(data)
+    np.unique(nan_xy)
+    counter = {y: 0. for y in np.unique(nan_xy.T[1])}
+    change_in_percentage = 1./size
+    for _, y in nan_xy:
+        counter[y] += change_in_percentage
+    total_missing = len(nan_xy)/size
+    counter["total"] = total_missing
+
+    return counter

impyute/contrib/describe.py

@@ -0,0 +1,63 @@
+""" impyute.contrib.describe """
+from impyute.ops import matrix
+
+def describe(data): # verbose=True):
+    """ Print input/output multiple times
+
+    Eventually will be used instead of matrix.nan_indices everywhere
+
+    Parameters
+    ----------
+    data: numpy.nd.array
+        The data you want to get a description from
+    verbose: boolean(optional)
+        Decides whether the description is short or long form
+
+    Returns
+    -------
+    dict
+        missingness: list
+            Confidence interval of data being MCAR, MAR or MNAR - in that order
+        nan_xy: list of tuples
+            Indices of all null points
+        nan_n: list
+            Total number of null values for each column
+        pmissing_n: float
+            Percentage of missing values in dataset
+        nan_rows: list
+            Indices of all rows that are completely null
+        nan_cols: list
+            Indices of all columns that are completely null
+        mean_rows: list
+            Mean value of each row
+        mean_cols: list
+            Mean value of each column
+        std_dev: list
+            std dev for each row/column
+        min_max: list
+            Finds the minimum and maximum for each row
+
+    """
+#    missingness = [0.33, 0.33, 0.33]  # find_missingness(data)
+    nan_xy = matrix.nan_indices(data)
+    nan_n = len(nan_xy)
+    pmissing_n = float(nan_n/len(data.flatten))
+#    pmissing_rows = ""
+#    pmissing_cols = ""
+#    nan_rows = ""
+#    nan_cols = ""
+#    mean_rows = ""
+#    mean_cols = ""
+#    std_dev = ""
+#                   "missingness": missingness,
+    description = {"nan_xy": nan_xy,
+                   "nan_n": nan_n,
+                   "pmissing_n": pmissing_n}
+#                   "pmissing_rows": pmissing_rows,
+#                   "pmissing_cols": pmissing_cols,
+#                   "nan_rows": nan_rows,
+#                   "nan_cols": nan_cols,
+#                   "mean_rows": mean_rows,
+#                   "mean_cols": mean_cols,
+#                   "std_dev": std_dev}
+    return description

impyute/cs/__init__.py

@@ -0,0 +1,11 @@
+""" Imputations for cross-sectional data.  """
+
+from .random import random_impute
+from .central_tendency import mean
+from .central_tendency import mode
+from .central_tendency import median
+from .buck_iterative import buck_iterative
+from .em import em
+from .fast_knn import fast_knn
+
+__all__ = ["random_impute", "mean", "mode", "median", "buck_iterative", "em", "fast_knn"]

impyute/cs/buck_iterative.py

@@ -0,0 +1,82 @@
+import numpy as np
+from sklearn.linear_model import LinearRegression
+from impyute.ops import matrix
+from impyute.ops import wrapper
+# pylint: disable=too-many-locals
+
+@wrapper.wrappers
+@wrapper.checks
+def buck_iterative(data):
+    """ Iterative variant of buck's method
+
+    - Variable to regress on is chosen at random.
+    - EM type infinite regression loop stops after change in prediction from
+      previous prediction < 10% for all columns with missing values
+
+    A Method of Estimation of Missing Values in Multivariate Data Suitable for
+    use with an Electronic Computer S. F. Buck Journal of the Royal Statistical
+    Society. Series B (Methodological) Vol. 22, No. 2 (1960), pp. 302-306
+
+    Parameters
+    ----------
+    data: numpy.ndarray
+        Data to impute.
+
+    Returns
+    -------
+    numpy.ndarray
+        Imputed data.
+
+    """
+    nan_xy = matrix.nan_indices(data)
+
+    # Add a column of zeros to the index values
+    nan_xyz = np.append(nan_xy, np.zeros((np.shape(nan_xy)[0], 1)), axis=1)
+
+    nan_xyz = [[int(x), int(y), v] for x, y, v in nan_xyz]
+    temp = []
+    cols_missing = {y for _, y, _ in nan_xyz}
+
+    # Step 1: Simple Imputation, these are just placeholders
+    for x_i, y_i, value in nan_xyz:
+        # Column containing nan value without the nan value
+        col = data[:, [y_i]][~np.isnan(data[:, [y_i]])]
+
+        new_value = np.mean(col)
+        data[x_i][y_i] = new_value
+        temp.append([x_i, y_i, new_value])
+    nan_xyz = temp
+
+    # Step 5: Repeat step 2 - 4 until convergence (the 100 is arbitrary)
+
+    converged = [False] * len(nan_xyz)
+    while not all(converged):
+        # Step 2: Placeholders are set back to missing for one variable/column
+        dependent_col = int(np.random.choice(list(cols_missing)))
+        missing_xs = [int(x) for x, y, value in nan_xyz if y == dependent_col]
+
+        # Step 3: Perform linear regression using the other variables
+        x_train, y_train = [], []
+        for x_i in (x_i for x_i in range(len(data)) if x_i not in missing_xs):
+            x_train.append(np.delete(data[x_i], dependent_col))
+            y_train.append(data[x_i][dependent_col])
+        model = LinearRegression()
+        model.fit(x_train, y_train)
+
+        # Step 4: Missing values for the missing variable/column are replaced
+        # with predictions from our new linear regression model
+        # For null indices with the dependent column that was randomly chosen
+        for i, z in enumerate(nan_xyz):
+            x_i = z[0]
+            y_i = z[1]
+            value = data[x_i, y_i]
+            if y_i == dependent_col:
+                # Row 'x' without the nan value
+                new_value = model.predict([np.delete(data[x_i], dependent_col)])
+                data[x_i][y_i] = new_value.reshape(1, -1)
+                if value == 0.0:
+                    delta = (new_value-value)/0.01
+                else:
+                    delta = (new_value-value)/value
+                converged[i] = abs(delta) < 0.1
+    return data