Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+datos_iniciales/nombres_apellido_nombres.json filter=lfs diff=lfs merge=lfs -text
+prediccion/Prediccion_nombres_apellido_nombres.xlsx filter=lfs diff=lfs merge=lfs -text

LICENSE

@@ -0,0 +1,339 @@
+                    GNU GENERAL PUBLIC LICENSE
+                       Version 2, June 1991
+
+ Copyright (C) 1989, 1991 Free Software Foundation, Inc.,
+ 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
+ Everyone is permitted to copy and distribute verbatim copies
+ of this license document, but changing it is not allowed.
+
+                            Preamble
+
+  The licenses for most software are designed to take away your
+freedom to share and change it.  By contrast, the GNU General Public
+License is intended to guarantee your freedom to share and change free
+software--to make sure the software is free for all its users.  This
+General Public License applies to most of the Free Software
+Foundation's software and to any other program whose authors commit to
+using it.  (Some other Free Software Foundation software is covered by
+the GNU Lesser General Public License instead.)  You can apply it to
+your programs, too.
+
+  When we speak of free software, we are referring to freedom, not
+price.  Our General Public Licenses are designed to make sure that you
+have the freedom to distribute copies of free software (and charge for
+this service if you wish), that you receive source code or can get it
+if you want it, that you can change the software or use pieces of it
+in new free programs; and that you know you can do these things.
+
+  To protect your rights, we need to make restrictions that forbid
+anyone to deny you these rights or to ask you to surrender the rights.
+These restrictions translate to certain responsibilities for you if you
+distribute copies of the software, or if you modify it.
+
+  For example, if you distribute copies of such a program, whether
+gratis or for a fee, you must give the recipients all the rights that
+you have.  You must make sure that they, too, receive or can get the
+source code.  And you must show them these terms so they know their
+rights.
+
+  We protect your rights with two steps: (1) copyright the software, and
+(2) offer you this license which gives you legal permission to copy,
+distribute and/or modify the software.
+
+  Also, for each author's protection and ours, we want to make certain
+that everyone understands that there is no warranty for this free
+software.  If the software is modified by someone else and passed on, we
+want its recipients to know that what they have is not the original, so
+that any problems introduced by others will not reflect on the original
+authors' reputations.
+
+  Finally, any free program is threatened constantly by software
+patents.  We wish to avoid the danger that redistributors of a free
+program will individually obtain patent licenses, in effect making the
+program proprietary.  To prevent this, we have made it clear that any
+patent must be licensed for everyone's free use or not licensed at all.
+
+  The precise terms and conditions for copying, distribution and
+modification follow.
+
+                    GNU GENERAL PUBLIC LICENSE
+   TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION
+
+  0. This License applies to any program or other work which contains
+a notice placed by the copyright holder saying it may be distributed
+under the terms of this General Public License.  The "Program", below,
+refers to any such program or work, and a "work based on the Program"
+means either the Program or any derivative work under copyright law:
+that is to say, a work containing the Program or a portion of it,
+either verbatim or with modifications and/or translated into another
+language.  (Hereinafter, translation is included without limitation in
+the term "modification".)  Each licensee is addressed as "you".
+
+Activities other than copying, distribution and modification are not
+covered by this License; they are outside its scope.  The act of
+running the Program is not restricted, and the output from the Program
+is covered only if its contents constitute a work based on the
+Program (independent of having been made by running the Program).
+Whether that is true depends on what the Program does.
+
+  1. You may copy and distribute verbatim copies of the Program's
+source code as you receive it, in any medium, provided that you
+conspicuously and appropriately publish on each copy an appropriate
+copyright notice and disclaimer of warranty; keep intact all the
+notices that refer to this License and to the absence of any warranty;
+and give any other recipients of the Program a copy of this License
+along with the Program.
+
+You may charge a fee for the physical act of transferring a copy, and
+you may at your option offer warranty protection in exchange for a fee.
+
+  2. You may modify your copy or copies of the Program or any portion
+of it, thus forming a work based on the Program, and copy and
+distribute such modifications or work under the terms of Section 1
+above, provided that you also meet all of these conditions:
+
+    a) You must cause the modified files to carry prominent notices
+    stating that you changed the files and the date of any change.
+
+    b) You must cause any work that you distribute or publish, that in
+    whole or in part contains or is derived from the Program or any
+    part thereof, to be licensed as a whole at no charge to all third
+    parties under the terms of this License.
+
+    c) If the modified program normally reads commands interactively
+    when run, you must cause it, when started running for such
+    interactive use in the most ordinary way, to print or display an
+    announcement including an appropriate copyright notice and a
+    notice that there is no warranty (or else, saying that you provide
+    a warranty) and that users may redistribute the program under
+    these conditions, and telling the user how to view a copy of this
+    License.  (Exception: if the Program itself is interactive but
+    does not normally print such an announcement, your work based on
+    the Program is not required to print an announcement.)
+
+These requirements apply to the modified work as a whole.  If
+identifiable sections of that work are not derived from the Program,
+and can be reasonably considered independent and separate works in
+themselves, then this License, and its terms, do not apply to those
+sections when you distribute them as separate works.  But when you
+distribute the same sections as part of a whole which is a work based
+on the Program, the distribution of the whole must be on the terms of
+this License, whose permissions for other licensees extend to the
+entire whole, and thus to each and every part regardless of who wrote it.
+
+Thus, it is not the intent of this section to claim rights or contest
+your rights to work written entirely by you; rather, the intent is to
+exercise the right to control the distribution of derivative or
+collective works based on the Program.
+
+In addition, mere aggregation of another work not based on the Program
+with the Program (or with a work based on the Program) on a volume of
+a storage or distribution medium does not bring the other work under
+the scope of this License.
+
+  3. You may copy and distribute the Program (or a work based on it,
+under Section 2) in object code or executable form under the terms of
+Sections 1 and 2 above provided that you also do one of the following:
+
+    a) Accompany it with the complete corresponding machine-readable
+    source code, which must be distributed under the terms of Sections
+    1 and 2 above on a medium customarily used for software interchange; or,
+
+    b) Accompany it with a written offer, valid for at least three
+    years, to give any third party, for a charge no more than your
+    cost of physically performing source distribution, a complete
+    machine-readable copy of the corresponding source code, to be
+    distributed under the terms of Sections 1 and 2 above on a medium
+    customarily used for software interchange; or,
+
+    c) Accompany it with the information you received as to the offer
+    to distribute corresponding source code.  (This alternative is
+    allowed only for noncommercial distribution and only if you
+    received the program in object code or executable form with such
+    an offer, in accord with Subsection b above.)
+
+The source code for a work means the preferred form of the work for
+making modifications to it.  For an executable work, complete source
+code means all the source code for all modules it contains, plus any
+associated interface definition files, plus the scripts used to
+control compilation and installation of the executable.  However, as a
+special exception, the source code distributed need not include
+anything that is normally distributed (in either source or binary
+form) with the major components (compiler, kernel, and so on) of the
+operating system on which the executable runs, unless that component
+itself accompanies the executable.
+
+If distribution of executable or object code is made by offering
+access to copy from a designated place, then offering equivalent
+access to copy the source code from the same place counts as
+distribution of the source code, even though third parties are not
+compelled to copy the source along with the object code.
+
+  4. You may not copy, modify, sublicense, or distribute the Program
+except as expressly provided under this License.  Any attempt
+otherwise to copy, modify, sublicense or distribute the Program is
+void, and will automatically terminate your rights under this License.
+However, parties who have received copies, or rights, from you under
+this License will not have their licenses terminated so long as such
+parties remain in full compliance.
+
+  5. You are not required to accept this License, since you have not
+signed it.  However, nothing else grants you permission to modify or
+distribute the Program or its derivative works.  These actions are
+prohibited by law if you do not accept this License.  Therefore, by
+modifying or distributing the Program (or any work based on the
+Program), you indicate your acceptance of this License to do so, and
+all its terms and conditions for copying, distributing or modifying
+the Program or works based on it.
+
+  6. Each time you redistribute the Program (or any work based on the
+Program), the recipient automatically receives a license from the
+original licensor to copy, distribute or modify the Program subject to
+these terms and conditions.  You may not impose any further
+restrictions on the recipients' exercise of the rights granted herein.
+You are not responsible for enforcing compliance by third parties to
+this License.
+
+  7. If, as a consequence of a court judgment or allegation of patent
+infringement or for any other reason (not limited to patent issues),
+conditions are imposed on you (whether by court order, agreement or
+otherwise) that contradict the conditions of this License, they do not
+excuse you from the conditions of this License.  If you cannot
+distribute so as to satisfy simultaneously your obligations under this
+License and any other pertinent obligations, then as a consequence you
+may not distribute the Program at all.  For example, if a patent
+license would not permit royalty-free redistribution of the Program by
+all those who receive copies directly or indirectly through you, then
+the only way you could satisfy both it and this License would be to
+refrain entirely from distribution of the Program.
+
+If any portion of this section is held invalid or unenforceable under
+any particular circumstance, the balance of the section is intended to
+apply and the section as a whole is intended to apply in other
+circumstances.
+
+It is not the purpose of this section to induce you to infringe any
+patents or other property right claims or to contest validity of any
+such claims; this section has the sole purpose of protecting the
+integrity of the free software distribution system, which is
+implemented by public license practices.  Many people have made
+generous contributions to the wide range of software distributed
+through that system in reliance on consistent application of that
+system; it is up to the author/donor to decide if he or she is willing
+to distribute software through any other system and a licensee cannot
+impose that choice.
+
+This section is intended to make thoroughly clear what is believed to
+be a consequence of the rest of this License.
+
+  8. If the distribution and/or use of the Program is restricted in
+certain countries either by patents or by copyrighted interfaces, the
+original copyright holder who places the Program under this License
+may add an explicit geographical distribution limitation excluding
+those countries, so that distribution is permitted only in or among
+countries not thus excluded.  In such case, this License incorporates
+the limitation as if written in the body of this License.
+
+  9. The Free Software Foundation may publish revised and/or new versions
+of the General Public License from time to time.  Such new versions will
+be similar in spirit to the present version, but may differ in detail to
+address new problems or concerns.
+
+Each version is given a distinguishing version number.  If the Program
+specifies a version number of this License which applies to it and "any
+later version", you have the option of following the terms and conditions
+either of that version or of any later version published by the Free
+Software Foundation.  If the Program does not specify a version number of
+this License, you may choose any version ever published by the Free Software
+Foundation.
+
+  10. If you wish to incorporate parts of the Program into other free
+programs whose distribution conditions are different, write to the author
+to ask for permission.  For software which is copyrighted by the Free
+Software Foundation, write to the Free Software Foundation; we sometimes
+make exceptions for this.  Our decision will be guided by the two goals
+of preserving the free status of all derivatives of our free software and
+of promoting the sharing and reuse of software generally.
+
+                            NO WARRANTY
+
+  11. BECAUSE THE PROGRAM IS LICENSED FREE OF CHARGE, THERE IS NO WARRANTY
+FOR THE PROGRAM, TO THE EXTENT PERMITTED BY APPLICABLE LAW.  EXCEPT WHEN
+OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES
+PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED
+OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
+MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE.  THE ENTIRE RISK AS
+TO THE QUALITY AND PERFORMANCE OF THE PROGRAM IS WITH YOU.  SHOULD THE
+PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF ALL NECESSARY SERVICING,
+REPAIR OR CORRECTION.
+
+  12. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
+WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY AND/OR
+REDISTRIBUTE THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES,
+INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING
+OUT OF THE USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED
+TO LOSS OF DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY
+YOU OR THIRD PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER
+PROGRAMS), EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE
+POSSIBILITY OF SUCH DAMAGES.
+
+                     END OF TERMS AND CONDITIONS
+
+            How to Apply These Terms to Your New Programs
+
+  If you develop a new program, and you want it to be of the greatest
+possible use to the public, the best way to achieve this is to make it
+free software which everyone can redistribute and change under these terms.
+
+  To do so, attach the following notices to the program.  It is safest
+to attach them to the start of each source file to most effectively
+convey the exclusion of warranty; and each file should have at least
+the "copyright" line and a pointer to where the full notice is found.
+
+    <one line to give the program's name and a brief idea of what it does.>
+    Copyright (C) <year>  <name of author>
+
+    This program is free software; you can redistribute it and/or modify
+    it under the terms of the GNU General Public License as published by
+    the Free Software Foundation; either version 2 of the License, or
+    (at your option) any later version.
+
+    This program is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU General Public License for more details.
+
+    You should have received a copy of the GNU General Public License along
+    with this program; if not, write to the Free Software Foundation, Inc.,
+    51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
+
+Also add information on how to contact you by electronic and paper mail.
+
+If the program is interactive, make it output a short notice like this
+when it starts in an interactive mode:
+
+    Gnomovision version 69, Copyright (C) year name of author
+    Gnomovision comes with ABSOLUTELY NO WARRANTY; for details type `show w'.
+    This is free software, and you are welcome to redistribute it
+    under certain conditions; type `show c' for details.
+
+The hypothetical commands `show w' and `show c' should show the appropriate
+parts of the General Public License.  Of course, the commands you use may
+be called something other than `show w' and `show c'; they could even be
+mouse-clicks or menu items--whatever suits your program.
+
+You should also get your employer (if you work as a programmer) or your
+school, if any, to sign a "copyright disclaimer" for the program, if
+necessary.  Here is a sample; alter the names:
+
+  Yoyodyne, Inc., hereby disclaims all copyright interest in the program
+  `Gnomovision' (which makes passes at compilers) written by James Hacker.
+
+  <signature of Ty Coon>, 1 April 1989
+  Ty Coon, President of Vice
+
+This General Public License does not permit incorporating your program into
+proprietary programs.  If your program is a subroutine library, you may
+consider it more useful to permit linking proprietary applications with the
+library.  If this is what you want to do, use the GNU Lesser General
+Public License instead of this License.

README.md

@@ -1,12 +1,2 @@
----
-title: Dannel Name2gender
-emoji: 🏆
-colorFrom: yellow
-colorTo: gray
-sdk: gradio
-sdk_version: 4.38.1
-app_file: app.py
-pinned: false
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# modelo_ML_Prediccion_Genero
+Modelo inicial contemplado para realizar la predicción de género basado en el nombre de la persona

datos_iniciales/nombres_apellido_nombres.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:422202a6802fdc494be3538b9e2e01c9cd4a18a7fc85383ef2a456fc9de0a4e2
+size 19701892

modelo/modelo_prediccion_genero_ml_dt.py

@@ -0,0 +1,197 @@
+# -*- coding: utf-8 -*-
+"""
+Archivo Python adaptado desde el notebook de databricks dispuesto desde el servicio de Azure-Data Sandbox
+Created on Mon Feb 15 22:14:16 2021
+@author: Carlos Delgado
+"""
+
+## Configrurando el storage account key
+
+
+storage_account_name = "Storage Account"
+storage_account_key = "Storage Account Key"
+container = "Storage Account Source Container"
+container_raw = "Storage Account Source Container Raw"
+
+
+dbutils.fs.ls("abfss://raw@stupramonitoreomercado.dfs.core.windows.net/OTROS/SNR/JSON/")
+dbutils.fs.ls("abfss://sandbox@stupramonitoreomercado.dfs.core.windows.net/OTROS/SNR/nombres_entrenamiento_espanol_filtrados/")
+
+# Algoritmo adaptado basado en https://nlpforhackers.io/introduction-machine-learning/ y adaptado del repositorio https://github.com/Jcharis/Python-Machine-Learning/tree/master/Gender%20Classification%20With%20%20Machine%20Learning
+
+#importando librerias iniciales de administracion de datos
+import pandas as pd
+import numpy as np
+
+#importando libreria y paquedes de ML desde Scikit-learn
+from sklearn.feature_extraction.text import CountVectorizer
+from sklearn.feature_extraction import DictVectorizer
+from sklearn.model_selection import train_test_split
+from sklearn.tree import DecisionTreeClassifier
+
+from pyspark.sql.functions import *
+from pyspark.sql.types import *
+
+df_original = spark.read.csv("abfss://sandbox@stupramonitoreomercado.dfs.core.windows.net/OTROS/SNR/nombres_entrenamiento_espanol_filtrados/nombres_entrenamiento_filtrados_v2.csv",header=True)
+display(df_original)
+
+#almacenando los nombres por genero a pandas dataframes
+df_pd_nombres_mf_general = df_original.select("*").toPandas()
+df_pd_nombres_mf_general.head()
+
+# Limpieza de datos
+# Verificando consistencia de columnnas 
+print(df_pd_nombres_mf_general.columns)
+
+# Verificando tipos de datos
+print(df_pd_nombres_mf_general.dtypes)
+
+# Verificando valores nulos
+print(df_pd_nombres_mf_general.isnull().isnull().sum())
+
+# Numero de nombres femeninos
+print("Numero de nombres femeninos: %s" %(len(df_pd_nombres_mf_general[df_pd_nombres_mf_general.SEXO == 'FEMENINO'])))
+# Numero de nombres masculinos
+print("Numero de nombres masculinos: %s" %(len(df_pd_nombres_mf_general[df_pd_nombres_mf_general.SEXO == 'MASCULINO'])))
+
+df_names = df_pd_nombres_mf_general
+
+# Remplazando con ceros y unos.
+df_names.SEXO.replace({'FEMENINO':0,'MASCULINO':1},inplace=True)
+df_names.SEXO.unique()
+df_names.dtypes
+
+Xfeatures = df_pd_nombres_mf_general['PRIMER_NOMBRE']
+
+#Extraccion de las características del df vectorizando
+cv = CountVectorizer()
+X = cv.fit_transform(Xfeatures.values.astype('U')) #Con el fin de no generar problemas en nombres con determinados carcateres 
+cv.get_feature_names()
+
+# Conformando el diccionario con la extraccion de las primeras y ultimas letras de cada uno de los nombres
+def features(name):
+    name = name.lower()
+    return {
+        'first-letter': name[0], # Primera letra
+        'first2-letters': name[0:2], # Primeras 2 letras
+        'first3-letters': name[0:3], # Primeras 3 letras
+        'last-letter': name[-1], # Ultima letra
+        'last2-letters': name[-2:], # Ultimas dos letras
+        'last3-letters': name[-3:], # Ultimas tres letras
+    }
+
+# Vectorize the features function
+features = np.vectorize(features)
+#Ejemplo
+print(features(["Anna", "Camilo", "Antonio","Margarita","Judith","Samuel"]))
+
+#Extrayendo las características para el conjunto de datos vectorizado
+df_X = features(df_names['PRIMER_NOMBRE'].values.astype('U'))
+df_y = df_names['SEXO']
+
+#Ejemplo
+arreglo = features(["Mike", "Julia"])
+dv = DictVectorizer()
+dv.fit(arreglo)
+transformed = dv.transform(arreglo)
+print(transformed)
+
+dv.get_feature_names()
+
+# Partiendo porcentaje de entrenamiento y testeo
+dfX_train, dfX_test, dfy_train, dfy_test = train_test_split(df_X, df_y, test_size=0.2, random_state=42)
+dfX_train
+dv = DictVectorizer()
+dv.fit_transform(dfX_train)
+
+#Definicion del clasificador Decision Trees
+dclf = DecisionTreeClassifier()
+my_xfeatures = dv.transform(dfX_train)
+dclf.fit(my_xfeatures, dfy_train)
+
+#Creacion de la funcion para mayor facilidad
+def prediccionGenero(a):
+    test_name1 = [a]
+    transform_dv =dv.transform(features(test_name1))
+    vector = transform_dv.toarray()
+    
+    if dclf.predict(vector) == 0:
+        #print("Female")
+        return "FEMENINO"
+    else:
+        #print("Male")
+        return("MASCULINO")
+
+#Calculando precisión (Accuracy) del modelo teniendo en cuenta los datos de entrenamiento
+print("Accuracy sobre los datos de entrenamiento: %s" %(dclf.score(dv.transform(dfX_train), dfy_train)))
+
+#Calculando precisión (Accuracy) del modelo teniendo en cuenta los datos testeo
+print("Accuracy sobre los datos de testeo: %s" %(dclf.score(dv.transform(dfX_test), dfy_test)))
+
+dbutils.fs.mount(
+  source = "wasbs://standarized@stupramonitoreomercado.blob.core.windows.net",
+  mount_point = "/mnt/auxiliar_2",
+  extra_configs = {"fs.azure.account.key.stupramonitoreomercado.blob.core.windows.net":"GlhaYCap6LQYbAwFb8PF3nzT3iPsjbTV6DmMB8rG08ms4R4KPcBn2Y3Y0p4OAtLCTqk8NS80y2tfBe0Ga2El7w=="}
+)
+
+import pickle
+from sklearn.externals import joblib
+import tempfile
+import os
+from joblib import dump, load
+
+s = pickle.dumps(dclf)
+classifier2 = pickle.loads(s)
+tmpFile = tempfile.NamedTemporaryFile(delete=False)
+dump(dclf, tmpFile)
+tmpFile.flush()
+#print(clf2)
+
+#copiando el modelo en pkl desde el punto de montaje al datalake
+dump(classifier2, '/tmp/modelo_gender_pred_dt.pkl') 
+dbutils.fs.cp('file:/tmp/modelo_gender_pred_dt.pkl', '/mnt/auxiliar_2/OTROS/SNR/modelo_gender_pred_dt_dl.pkl')
+
+dbutils.fs.cp('/mnt/auxiliar_2/OTROS/SNR/modelo_gender_pred_dt_dl.pkl', '/tmp/modelo_gender_pred_dt_saved.pkl', )
+display(dbutils.fs.ls ("/tmp/"))
+classifier_Final = joblib.load('/dbfs/tmp/modelo_gender_pred_dt_saved.pkl')
+
+#leyendo el archivo desde el json del storage y alamcenandolo como pandas dataframe
+dbutils.fs.ls("abfss://sandbox@stupramonitoreomercado.dfs.core.windows.net/OTROS/SNR/")
+#df_from_json = spark.read.json("abfss://sandbox@stupramonitoreomercado.dfs.core.windows.net/OTROS/SNR/nombres_apellido_nombre.json")
+#df_from_json = spark.read.json("abfss://sandbox@stupramonitoreomercado.dfs.core.windows.net/OTROS/SNR/nombres_comunes_masculino_femenino.json")
+df_from_json = spark.read.json("abfss://standarized@stupramonitoreomercado.dfs.core.windows.net/OTROS/SNR/intervinientes_clean_sexo_nombres_rurales_pendientes_modelo_similaridad.json")
+
+display(df_from_json)
+
+df_to_predict = df_from_json.select("*").toPandas()
+df_to_predict.head()
+
+#Prediccion de los nuevos nombres que se le presentan al modelo
+final_gender = []
+
+#for item in df_to_predict.NOMBRES:
+for item in df_to_predict.PRIMER_NOMBRE:
+    #print("Nombre: %s ---- Genero: %s" %(item,clf.predict((item, ))))
+    if pd.isnull(item) == True or item == '':
+        final_gender.append("")
+    else:
+        final_gender.append(prediccionGenero(item))
+
+#Campo donde se almacena la predicción de los nombres 
+df_to_predict['PREDICCION'] = final_gender
+display(df_to_predict)
+
+df_final_Selection = df_to_predict[['id','PRIMER_NOMBRE','SEXO','PREDICCION', 'TIPO_CLASIFICACION']]
+df_no_similarity = df_final_Selection[df_final_Selection['TIPO_CLASIFICACION'].isnull()]
+df_no_similarity['TIPO_CLASIFICACION'] = 'MODELO_ML'
+df_no_similarity.SEXO = np.where(df_no_similarity.SEXO.isnull(), df_no_similarity.PREDICCION, df_no_similarity.SEXO)
+
+final_table_to_export = df_no_similarity[['id','PRIMER_NOMBRE','SEXO','TIPO_CLASIFICACION']]
+display(df_final_Selection)
+display(final_table_to_export)
+print("Numero de nombres que fueron predecidos: %s" %(len(final_table_to_export)))
+
+#Guardando los reusltados de la predicción en CSV hacia el data lake
+#df_to_predict.to_csv('/tmp/Prediccion_nombres_apellido_nombre.csv', index=False)
+df_to_predict.to_csv('/tmp/prediccion_intervinientes_clean_sexo_nombres_rurales_pendientes_modelo_ml_v1.csv', index=False)
+dbutils.fs.cp('file:/tmp/prediccion_intervinientes_clean_sexo_nombres_rurales_pendientes_modelo_ml_v1.csv', '/mnt/auxiliar_2/OTROS/SNR/prediccion_intervinientes_clean_sexo_nombres_rurales_pendientes_modelo_ml_v1.csv')

modelo/modelo_prediccion_genero_ml_nb.py

@@ -0,0 +1,233 @@
+# -*- coding: utf-8 -*-
+"""
+Archivo Python adaptado desde el notebook de databricks dispuesto desde el servicio de Azure-Data Sandbox
+Created on Mon Dec 14 08:18:00 2020
+@author: Carlos Delgado
+"""
+
+## Configrurando el storage account key
+
+
+storage_account_name = "Storage Account"
+storage_account_key = "Storage Account Key"
+container = "Storage Account Source Container"
+container_raw = "Storage Account Source Container Raw"
+
+spark.conf.set("fs.azure.account.key.{0}.dfs.core.windows.net".format(storage_account_name), storage_account_key)
+spark.conf.set("fs.azure.createRemoteFileSystemDuringInitialization", "true")
+dbutils.fs.ls("abfss://{0}@{1}.dfs.core.windows.net/".format(container_raw, storage_account_name))
+spark.conf.set("fs.azure.createRemoteFileSystemDuringInitialization", "false")
+
+
+## Examinando el listado de archivos
+
+dbutils.fs.ls("abfss://{0}@{1}.dfs.core.windows.net/OTROS/SNR/JSON/".format(container_raw, storage_account_name))
+dbutils.fs.ls("abfss://{0}@{1}.dfs.core.windows.net/OTROS/KAGGLE/nombres_espanol_entrenamiento_test1/".format(container, storage_account_name))
+
+
+## Importanto las principales librerias utilizadas en el algoritmo de predicción
+
+# Algoritmo adaptado de https://www.kaggle.com/migalpha/gender-predictor-by-spanish-names
+#importando librerias iniciales
+import pandas as pd
+import numpy as np
+
+#importando libreria de AI Scikit-learn
+from sklearn.model_selection import train_test_split
+
+
+## Obtencion de los datos iniciales desde el csv con spark
+
+from pyspark.sql.functions import *
+from pyspark.sql.types import *
+
+df_fem_original = spark.read.csv("abfss://{0}@{1}.dfs.core.windows.net/OTROS/KAGGLE/nombres_espanol_entrenamiento_test1/female_names.csv".format(container, storage_account_name),header=True)
+df_mal_original = spark.read.csv("abfss://{0}@{1}.dfs.core.windows.net/OTROS/KAGGLE/nombres_espanol_entrenamiento_test1/male_names.csv".format(container, storage_account_name),header=True)
+display(df_fem_original)
+display(df_mal_original)
+
+
+
+## Migrando de Spark dataframes a Pandas dtaframes
+
+#almacenando los nombres por genero a pandas dataframes
+fem_nombres = df_fem_original.select("*").toPandas()
+mal_nombres = df_mal_original.select("*").toPandas()
+
+
+## Instanciando variables
+
+#asignación de indicadores para genero, 0 femenino, 1 masculino
+fem_nombres['genero'] = 0
+mal_nombres['genero'] = 1
+
+
+#unificación de conjunto de datos eliminando potenciales duplicados
+data = fem_nombres.append(mal_nombres, ignore_index=True)
+data = data.drop_duplicates(subset='name', keep=False)
+
+#parceando y limpiando atributos innecesarios
+
+target = data['genero'].astype(str)
+
+del(data['frequency'])
+del(data['mean_age'])
+del(data['genero'])
+
+features = data['name'].astype(str)
+
+
+## Configurando el modelo del modelo
+
+#se dividen los datos 80% entrenamiento - 20% testeo
+
+X_train, X_test, y_train, y_test = train_test_split(features, target, random_state=7, test_size=0.2)
+print(X_train.shape, X_test.shape, y_train.shape, y_test.shape)
+
+#libreria para extraer caracteristicas de los archivos de texto
+from sklearn.feature_extraction.text import CountVectorizer
+
+#TF-IDF Esta librería se encarga de transformar una matriz de conteo de ocurrencias (term-frequency)  a una matriz normalizada de ocurrencias ( term-frequency times inverse document-frequency)
+#Mayor documentación tecnica en https://scikit-learn.org/stable/modules/generated/sklearn.feature_extraction.text.TfidfTransformer.html
+from sklearn.feature_extraction.text import TfidfTransformer
+
+#importando clasificador ML Naive Bayes NB
+from sklearn.naive_bayes import MultinomialNB
+
+
+#creando el pipeline
+from sklearn.pipeline import Pipeline
+
+text_classifier = Pipeline([('vect', CountVectorizer(ngram_range=(1,1))), ('tfidf',TfidfTransformer(norm='l2', sublinear_tf=True, use_idf=False)), ('clf', MultinomialNB(alpha=0.1))])
+
+
+## Entrenamiento del modelo y calculo de accuracy
+
+#entrenando el modelo
+text_classifier = text_classifier.fit(X_train, y_train)
+
+#calculando precisión del modelo utilizando el clasificador NB
+from sklearn.metrics import accuracy_score
+predicted = text_classifier.predict(X_test)
+
+print(accuracy_score(y_test, predicted))
+
+
+
+## Testeando el modelo
+
+#importando GridSearchCV para seleccionar los mejores hiperparametros
+from sklearn.model_selection import GridSearchCV
+parameters = {
+        #'vect__max_df': (0.5, 0.625, 0.75, 0.875, 1.0),  
+        #'vect__max_features': (None, 5000, 10000, 20000),  
+        #'vect__min_df': (1, 5, 10, 20, 50),  
+        'vect__ngram_range': [(1, 1), (1, 2)], 
+        'tfidf__use_idf': (True, False),
+        'tfidf__sublinear_tf': (True, False),  
+        #'vect__binary': (True, False),  
+        'tfidf__norm': ('l1', 'l2'),  
+        'clf__alpha': (1, 0.1, 0.01, 0.001, 0.0001, 0.00001)
+}
+
+gs_classifier = GridSearchCV(text_classifier, parameters, n_jobs=-1, cv=2)
+gs_classifier = gs_classifier.fit(X_train, y_train)
+
+print(gs_classifier.best_score_)
+print(gs_classifier.best_params_)
+
+
+## Generación del punto de montaje
+
+#testeando punto de montaje, el montaje se esta ejecutando satisfactoriamente
+
+dbutils.fs.mount(
+  source = "wasbs://{0}@{1}.blob.core.windows.net".format(container, storage_account_name),
+  mount_point = "/mnt/auxiliar",
+  extra_configs = {"fs.azure.account.key.{0}.blob.core.windows.net".format(storage_account_name):storage_account_key}
+)
+
+
+## Salvando el modelo como archivo de pickle .pkl
+
+
+import pickle
+from sklearn.externals import joblib
+import tempfile
+import os
+from joblib import dump, load
+
+#model_path = "/mnt/auxiliar/modelo_gender_pred.pkl"
+s = pickle.dumps(text_classifier)
+classifier2 = pickle.loads(s)
+tmpFile = tempfile.NamedTemporaryFile(delete=False)
+dump(text_classifier, tmpFile)
+tmpFile.flush()
+#print(clf2)
+
+#copiando el modelo en pkl desde el punto de montaje al datalake
+dump(classifier2, '/tmp/modelo_gender_pred.pkl') 
+dbutils.fs.cp('file:/tmp/modelo_gender_pred.pkl', '/mnt/auxiliar/OTROS/KAGGLE/nombres_espanol_entrenamiento_test1/modelo_gender_pred_data_lake.pkl')
+
+dbutils.fs.cp('/mnt/auxiliar/OTROS/KAGGLE/nombres_espanol_entrenamiento_test1/modelo_gender_pred_data_lake.pkl', '/tmp/modelo_gender_saved.pkl', )
+display(dbutils.fs.ls ("/tmp/"))
+classifier_Final = joblib.load('/dbfs/tmp/modelo_gender_saved.pkl')
+
+
+#testeando algunas predicciones desde el modelo almacenado
+
+print(classifier_Final.predict(("Valentina", )))
+print(classifier_Final.predict(("Miguel", )))
+print(classifier_Final.predict(("Maria", )))
+print(classifier_Final.predict(("Joe", )))
+print(classifier_Final.predict(("Santiago", )))
+print(classifier_Final.predict(("Magdalena", )))
+
+
+## Prediccion - Leyendo el archivo para prediccion
+
+#leyendo el archivo desde el json del storage y alamcenandolo como pandas dataframe
+dbutils.fs.ls("abfss://{0}@{1}.dfs.core.windows.net/OTROS/SNR/".format(container, storage_account_name))
+#df_from_json = spark.read.json("abfss://{0}@{1}.dfs.core.windows.net/OTROS/SNR/nombres_apellido_nombre.json")
+df_from_json = spark.read.json("abfss://{0}@{1}.dfs.core.windows.net/OTROS/SNR/nombres_para_clasificar.json".format(container, storage_account_name))
+
+
+
+display(df_from_json)
+
+df_to_predict = df_from_json.select("*").toPandas()
+df_to_predict.head()
+
+
+## Ejecutando la prediccion de los genereros
+
+#Prediccion de los nuevos nombres que se le presentan al modelo
+final_gender = []
+
+#for item in df_to_predict.NOMBRES:
+for item in df_to_predict.PRIMER_NOMBRE:
+    #print("Nombre: %s ---- Genero: %s" %(item,clf.predict((item, ))))
+    if pd.isnull(item) == True:
+        final_gender.append("")
+    elif clf.predict((item, ))[0] == '0':
+        #print("Mujer")
+        final_gender.append("MUJER")
+    else:
+        #print("Hombre")
+        final_gender.append("HOMBRE")
+
+#Campo donde se almacena la predicción de los nombres        
+df_to_predict['PREDICCION'] = final_gender
+
+display(df_to_predict)
+
+
+## Guardando los reusltados de la predicción en CSV hacia el data lake
+
+#df_to_predict.to_csv('/tmp/Prediccion_nombres_apellido_nombre.csv', index=False)
+df_to_predict.to_csv('/tmp/Prediccion_nombres_para_clasificar.csv', index=False)
+dbutils.fs.cp('file:/tmp/Prediccion_nombres_para_clasificar.csv', '/mnt/auxiliar/OTROS/KAGGLE/nombres_espanol_entrenamiento_test1/Prediccion_final_nombres_nombres_para_clasificar.csv')
+
+
+
+

prediccion/Prediccion_nombres_apellido_nombres.xlsx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0459c3fe75fa8a8ed65e6308ba96198921b5463ce0e341a819b692ea2ce07a89
+size 5873079