%load_ext autoreload
%autoreload 2

# First, I have to laod different modules that I use for analyzing the data and for plotting:
import sys, os, collections
import pandas as pd
import numpy as np
import seaborn as sns
import matplotlib.pyplot as plt; plt.rcdefaults()
import re
from matplotlib.pyplot import figure
from collections import Counter

# Second, I have to load the Text Fabric app
from tf.fabric import Fabric
from tf.app import use

pd.set_option('display.max_columns', None)

TotalVocab='''
word lex* bol_dict_HebArm* bol_dict_EN* number* freq_occ* rank_occ* bol_fa_order* bol_lexeme_occurrences* bol_dict_abc* language* bol_monad_num* qere_utf8* g_word_utf8* g_lex_utf8* bol_g_word_utf8* bol_qere_presence*

'''
TotalVocab  = BHSa4c.search(TotalVocab)
BHSa4c.table(TotalVocab, start=1, end=5, condensed=False, colorMap={1: 'cyan'})

BHSa4c.export(TotalVocab, toDir='/Users/oliverglanz/Library/CloudStorage/OneDrive-AndrewsUniversity/1200_AUS-research/Fabric-TEXT/2_OTST551-2_Hebrew/BOL_exercises', toFile='BHSa4c_BOL_vocab.tsv')

#BibleOL_verbal_morphology=pd.read_csv('/Users/oliverglanz/Library/CloudStorage/OneDrive-AndrewsUniversity/1200_AUS-research/Fabric-TEXT/2_OTST551-2 Hebrew/BHSa4c_BOL_exercises.tsv', delimiter='\t', encoding='utf-16')
TotalVocab=pd.read_csv('/Users/oliverglanz/Library/CloudStorage/OneDrive-AndrewsUniversity/1200_AUS-research/Fabric-TEXT/2_OTST551-2_Hebrew/BOL_exercises/BHSa4c_BOL_vocab.tsv', delimiter='\t', encoding='utf-16')
#BHSallWords=pd.read_csv('D:/OneDrive - Andrews University/1200_AUS-research/Fabric-TEXT/2_OTST551-2 Hebrew/BHSa4c_BOL_exercises.tsv', delimiter='\t', encoding='utf-16')

TotalVocab.head(20)

HebrewWordRank_BibleOL_Vocab='''
word lex* bol_dict_HebArm* bol_dict_EN number* g_word_noaccent* freq_occ* rank_occ* bol_fa_order* bol_dict_vc* sp* bol_lexeme_occurrences* bol_dict_abc* language* bol_monad_num* qere_utf8* g_word_utf8* g_lex_utf8* bol_g_word_utf8* bol_qere_presence*

'''
HebrewWordRank_BibleOL_Vocab  = BHSa4c.search(HebrewWordRank_BibleOL_Vocab)
BHSa4c.table(HebrewWordRank_BibleOL_Vocab, start=1, end=5, condensed=False, colorMap={1: 'cyan'})

BHSa4c.export(HebrewWordRank_BibleOL_Vocab, toDir='/Users/oliverglanz/Library/CloudStorage/OneDrive-AndrewsUniversity/1200_AUS-research/Fabric-TEXT/2_OTST551-2_Hebrew/BOL_exercises', toFile='BHSa4c_BOL_vocab_exercises_HebI-II-III.tsv')

#BibleOL_verbal_morphology=pd.read_csv('/Users/oliverglanz/Library/CloudStorage/OneDrive-AndrewsUniversity/1200_AUS-research/Fabric-TEXT/2_OTST551-2 Hebrew/BHSa4c_BOL_exercises.tsv', delimiter='\t', encoding='utf-16')
BHSallWords=pd.read_csv('/Users/oliverglanz/Library/CloudStorage/OneDrive-AndrewsUniversity/1200_AUS-research/Fabric-TEXT/2_OTST551-2_Hebrew/BOL_exercises/BHSa4c_BOL_vocab_exercises_HebI-II-III.tsv', delimiter='\t', encoding='utf-16')
#BHSallWords=pd.read_csv('D:/OneDrive - Andrews University/1200_AUS-research/Fabric-TEXT/2_OTST551-2 Hebrew/BHSa4c_BOL_exercises.tsv', delimiter='\t', encoding='utf-16')

BHSallWords.head()

BHSallHebrewWords=BHSallWords[(BHSallWords['language1']=='Hebrew') 
                              & (BHSallWords['bol_lexeme_occurrences1']>=40)
                              & (~BHSallWords['g_word_noaccent1'].astype(str).str.contains("^\*"))
                              & (~BHSallWords['bol_dict_vc1'].astype(str).str.contains("four.*verb"))

                             ]
BHSallHebrewWords.head() 

BHSallHebrewWords_selection_of_sequenced2=BHSallHebrewWords.groupby('bol_dict_HebArm1').nth((0,1,2)).sort_values(['rank_occ1','bol_dict_abc1'], ascending=True)
BHSallHebrewWords_selection_of_sequenced2.head()

BHSallHebrewWords_selection_of_random3=BHSallHebrewWords.groupby('bol_dict_HebArm1').sample(n=3, replace=True).sort_values(['rank_occ1','bol_dict_abc1'], ascending=True)
BHSallHebrewWords_selection_of_random3.head()

BHSallHebrewWords_selection_of_random3.to_excel('/Users/oliverglanz/Library/CloudStorage/OneDrive-AndrewsUniversity/1200_AUS-research/Fabric-TEXT/2_OTST551-2_Hebrew/BOL_exercises/OTST551_vocab_exercise-pool_Heb-I-II-III_vocab_selection_of_3.xlsx', encoding='utf-16')

#BibleOL_verbal_morphology=pd.read_csv('/Users/oliverglanz/Library/CloudStorage/OneDrive-AndrewsUniversity/1200_AUS-research/Fabric-TEXT/2_OTST551-2 Hebrew/BHSa4c_BOL_exercises.tsv', delimiter='\t', encoding='utf-16')
BHSallWords=pd.read_csv('/Users/oliverglanz/Library/CloudStorage/OneDrive-AndrewsUniversity/1200_AUS-research/Fabric-TEXT/2_OTST551-2_Hebrew/BOL_exercises/BHSa4c_BOL_vocab_exercises_HebI-II-III.tsv', delimiter='\t', encoding='utf-16')
#BHSallWords=pd.read_csv('D:/OneDrive - Andrews University/1200_AUS-research/Fabric-TEXT/2_OTST551-2 Hebrew/BHSa4c_BOL_exercises.tsv', delimiter='\t', enccoding='utf-16')

BHSallWords.head()

BHSallHebrewWords=BHSallWords[(BHSallWords['language1']=='Hebrew') & (BHSallWords['S1']=='Genesis')]
BHSallHebrewWords.head() 

Gen19v='''
verse book=Genesis chapter=19 verse=21|22|23|25|27|29|30
 word lex* bol_dict_HebArm* bol_dict_EN* number* freq_occ* rank_occ* bol_fa_order* bol_lexeme_occurrences* bol_dict_abc* language* bol_monad_num* qere_utf8* g_word_utf8* g_lex_utf8* bol_g_word_utf8* bol_qere_presence*

'''
Gen19v  = BHSa4c.search(Gen19v)
BHSa4c.table(Gen19v, start=1, end=5, condensed=False, colorMap={1: 'cyan'})

BHSa4c.export(Gen19v, toDir='/Users/oliverglanz/Library/CloudStorage/OneDrive-AndrewsUniversity/1200_AUS-research/Fabric-TEXT/2_OTST551-2_Hebrew/BOL_exercises', toFile='Gen19v.tsv')

#BibleOL_verbal_morphology=pd.read_csv('/Users/oliverglanz/Library/CloudStorage/OneDrive-AndrewsUniversity/1200_AUS-research/Fabric-TEXT/2_OTST551-2 Hebrew/BHSa4c_BOL_exercises.tsv', delimiter='\t', encoding='utf-16')
BHSallWords=pd.read_csv('/Users/oliverglanz/Library/CloudStorage/OneDrive-AndrewsUniversity/1200_AUS-research/Fabric-TEXT/2_OTST551-2_Hebrew/BOL_exercises/BHSa4c_BOL_vocab_exercises.tsv', delimiter='\t', encoding='utf-16')
#BHSallWords=pd.read_csv('D:/OneDrive - Andrews University/1200_AUS-research/Fabric-TEXT/2_OTST551-2 Hebrew/BHSa4c_BOL_exercises.tsv', delimiter='\t', encoding='utf-16')

BHSallWords.head()

BHSallHebrewWords=BHSallWords[(BHSallWords['language1']=='Hebrew') & (BHSallWords['S1']=='Psalms')]
BHSallHebrewWords.head()

OTST552Midterm_Vocab_Text01='''
verse book=Genesis chapter=20 verse=6|7|8|9
  w1:word bol_sequence_number_phrase* bol_sequence_number_phrase_atom* bol_lexeme_occurrences>100 bol_sequence_number_clause* bol_sequence_number_clause_atom* bol_monad_num*
  w2:word bol_lexeme_occurrences<6000

w1 = w2


'''
OTST552Midterm_Vocab_Text01  = BHSa4c.search(OTST552Midterm_Vocab_Text01)
BHSa4c.table(OTST552Midterm_Vocab_Text01, start=1, end=1, extraFeatures={'number'}, condensed=True, colorMap={13: 'cyan'})

BHSa4c.export(OTST552Midterm_Vocab_Text01, toDir='/Users/oliverglanz/Library/CloudStorage/OneDrive-AndrewsUniversity/1200_AUS-research/Fabric-TEXT/2_OTST551-2_Hebrew/BOL_exercises/', toFile='BHSa4c_BOL_vocabulary_Heb-II_Midterm_Vocab_Text01.tsv')

OTST552Midterm_Vocab_Text02='''
v1:verse book=Reges_I chapter=3 verse=3
  w1:word bol_sequence_number_phrase* bol_sequence_number_phrase_atom* bol_lexeme_occurrences>100 bol_sequence_number_clause* bol_sequence_number_clause_atom* bol_monad_num*
  w2:word bol_lexeme_occurrences<6000

w1 = w2


'''
OTST552Midterm_Vocab_Text02  = BHSa4c.search(OTST552Midterm_Vocab_Text02)
BHSa4c.table(OTST552Midterm_Vocab_Text02, start=1, end=1, extraFeatures={'number'}, condensed=True, colorMap={13: 'cyan'})

BHSa4c.export(OTST552Midterm_Vocab_Text02, toDir='/Users/oliverglanz/Library/CloudStorage/OneDrive-AndrewsUniversity/1200_AUS-research/Fabric-TEXT/2_OTST551-2_Hebrew/BOL_exercises/', toFile='BHSa4c_BOL_vocabulary_Heb-II_Midterm_Vocab_Text02.tsv')

Hebrew_PrefixingAll='''
c:clause
 w1:word lex=W g_word~^W:-|^W@-|^WI-|^WA-|^WE-     bol_dict_HebArm* number* freq_occ* rank_occ* freq_lex bol_dict_abc* language=Hebrew bol_monad_num
 w2:word g_word~^[>BGDHWZXVJKLMNS<PYQRFCT]:|^B|^M|^P|^J[>BGDHWZXVJKLMNS<PYQRFCT]|^[>HX<]:E|^[>HX<]:A|^[>HX<]:@ sp=subs|nmpr bol_monad_num

w1 <: w2


'''
Hebrew_PrefixingAll  = BHSa4c.search(Hebrew_PrefixingAll)
BHSa4c.table(Hebrew_PrefixingAll, start=1, end=10, condensed=False, colorMap={1: 'cyan'})

Hebrew_PrefixingW1='''
c:clause
 w1:word lex=W g_word~^W:-   bol_dict_HebArm* number* freq_occ* rank_occ* freq_lex bol_dict_abc* language=Hebrew bol_monad_num
 w2:word g_word~^[>BGDHWZXVJKLMNS<PYQRFCT][AIOU@E;][>BGDHWZXVJKLMNS<PYQRFCT].[>BGDHWZXVJKLMNS<PYQRFCT] sp=subs|nmpr bol_monad_num

w1 <: w2


'''
Hebrew_PrefixingW1  = BHSa4c.search(Hebrew_PrefixingW1)
BHSa4c.table(Hebrew_PrefixingW1, start=1, end=50, condensed=False, colorMap={1: 'cyan'})

BHSa4c.export(Hebrew_PrefixingW1, toDir='/Users/oliverglanz/Library/CloudStorage/OneDrive-AndrewsUniversity/1200_AUS-research/Fabric-TEXT/2_OTST551-2_Hebrew/BOL_exercises/', toFile='BHSa4c_BOL_morphology_prefixingW1_exercises.tsv')

Hebrew_PrefixingW1=pd.read_csv('/Users/oliverglanz/Library/CloudStorage/OneDrive-AndrewsUniversity/1200_AUS-research/Fabric-TEXT/2_OTST551-2_Hebrew/BOL_exercises/BHSa4c_BOL_morphology_prefixingW1_exercises.tsv', delimiter='\t', encoding='utf-16')
Hebrew_PrefixingW1.head()

## A first attempt to organize and sample the data
## We use `groupby`, a sequence of `sort_values`, and `nth` (to select only 2 entries per grouped category)

Hebrew_PrefixingW1selection=Hebrew_PrefixingW1 \
                                    .groupby(['TEXT2']) \
                                    .sample(n=5, replace=True)\
                                    .sort_values(['TEXT2','bol_monad_num2'], 
                                                 ascending=True)
Hebrew_PrefixingW1selection.head(10)

Hebrew_PrefixingW1selection.to_excel('/Users/oliverglanz/Library/CloudStorage/OneDrive-AndrewsUniversity/1200_AUS-research/Fabric-TEXT/2_OTST551-2_Hebrew/BOL_exercises/BHSa4c_BOL_Hebrew_morphology_PrefixingW1selection.xlsx', encoding='utf-16')

Hebrew_PrefixingW2='''
c:clause
 w1:word lex=W g_word~^W\.-     bol_dict_HebArm* number* freq_occ* rank_occ* freq_lex bol_dict_abc* language=Hebrew bol_monad_num
 w2:word g_word~^[>BGDHWZXVKLMNS<PYQRFCT]:[>BGDHWZXVJKLMNS<PYQRFCT][AIOUE;@]|^B[AIOUE;@][>BGDHWZXVJKLMNS<PYQRFCT]|^M[AIOUE;@][>BGDHWZXVJKLMNS<PYQRFCT]|^P[AIOUE;@][>BGDHWZXVJKLMNS<PYQRFCT] sp=subs|nmpr bol_monad_num

w1 <: w2


'''
Hebrew_PrefixingW2  = BHSa4c.search(Hebrew_PrefixingW2)
BHSa4c.table(Hebrew_PrefixingW2, start=1, end=50, condensed=False, colorMap={1: 'cyan'})

BHSa4c.export(Hebrew_PrefixingW2, toDir='/Users/oliverglanz/Library/CloudStorage/OneDrive-AndrewsUniversity/1200_AUS-research/Fabric-TEXT/2_OTST551-2_Hebrew/BOL_exercises/', toFile='BHSa4c_BOL_morphology_prefixingW2_exercises.tsv')

Hebrew_PrefixingW2=pd.read_csv('/Users/oliverglanz/Library/CloudStorage/OneDrive-AndrewsUniversity/1200_AUS-research/Fabric-TEXT/2_OTST551-2_Hebrew/BOL_exercises/BHSa4c_BOL_morphology_prefixingW2_exercises.tsv', delimiter='\t', encoding='utf-16')
Hebrew_PrefixingW2.head()

## A first attempt to organize and sample the data
## We use `groupby`, a sequence of `sort_values`, and `nth` (to select only 2 entries per grouped category)

Hebrew_PrefixingW2selection=Hebrew_PrefixingW2 \
                                    .groupby(['TEXT2']) \
                                    .sample(n=5, replace=True)\
                                    .sort_values(['TEXT2','bol_monad_num2'], 
                                                 ascending=True)
Hebrew_PrefixingW2selection.head(10)

Hebrew_PrefixingW2selection.to_excel('/Users/oliverglanz/Library/CloudStorage/OneDrive-AndrewsUniversity/1200_AUS-research/Fabric-TEXT/2_OTST551-2_Hebrew/BOL_exercises/BHSa4c_BOL_Hebrew_morphology_PrefixingW2selection.xlsx', encoding='utf-16')

Hebrew_PrefixingW3='''
c:clause
 w1:word lex=W g_word~^WI-     bol_dict_HebArm* number* freq_occ* rank_occ* freq_lex bol_dict_abc* language=Hebrew bol_monad_num
 w2:word g_word~^J[>BGDHWZXVJKLMNS<PYQRFCT][AIOUE@][>BGDHWZXVJKLMNS<PYQRFCT]|^J[>BGDHWZXVJKLMNS<PYQRFCT][W].|^J[>BGDHWZXVJKLMNS<PYQRFCT][J][IE] sp=subs|nmpr bol_monad_num

w1 <: w2


'''
Hebrew_PrefixingW3  = BHSa4c.search(Hebrew_PrefixingW3)
BHSa4c.table(Hebrew_PrefixingW3, start=1, end=50, condensed=False, colorMap={1: 'cyan'})

BHSa4c.export(Hebrew_PrefixingW3, toDir='/Users/oliverglanz/Library/CloudStorage/OneDrive-AndrewsUniversity/1200_AUS-research/Fabric-TEXT/2_OTST551-2_Hebrew/BOL_exercises/', toFile='BHSa4c_BOL_morphology_prefixingW3_exercises.tsv')

Hebrew_PrefixingW3=pd.read_csv('/Users/oliverglanz/Library/CloudStorage/OneDrive-AndrewsUniversity/1200_AUS-research/Fabric-TEXT/2_OTST551-2_Hebrew/BOL_exercises/BHSa4c_BOL_morphology_prefixingW3_exercises.tsv', delimiter='\t', encoding='utf-16')
Hebrew_PrefixingW3.head()

## A first attempt to organize and sample the data
## We use `groupby`, a sequence of `sort_values`, and `nth` (to select only 2 entries per grouped category)

Hebrew_PrefixingW3selection=Hebrew_PrefixingW3 \
                                    .groupby(['TEXT2']) \
                                    .sample(n=5, replace=True)\
                                    .sort_values(['TEXT2','bol_monad_num2'], 
                                                 ascending=True)
Hebrew_PrefixingW3selection.head(10)

Hebrew_PrefixingW3selection.to_excel('/Users/oliverglanz/Library/CloudStorage/OneDrive-AndrewsUniversity/1200_AUS-research/Fabric-TEXT/2_OTST551-2_Hebrew/BOL_exercises/BHSa4c_BOL_Hebrew_morphology_PrefixingW3selection.xlsx', encoding='utf-16')

Hebrew_PrefixingW4a='''
c:clause
 w1:word lex=W g_word~^W@- bol_dict_HebArm* number* freq_occ* rank_occ* freq_lex bol_dict_abc* language=Hebrew bol_monad_num
 w2:word g_word~^[>HX<]:@[>BGDHWZXVJKLMNS<PYQRFCT][AIOUE@] sp=subs|nmpr bol_monad_num

w1 <: w2


'''
Hebrew_PrefixingW4a  = BHSa4c.search(Hebrew_PrefixingW4a)
BHSa4c.table(Hebrew_PrefixingW4a, start=1, end=50, condensed=False, colorMap={1: 'cyan'})

BHSa4c.export(Hebrew_PrefixingW4a, toDir='/Users/oliverglanz/Library/CloudStorage/OneDrive-AndrewsUniversity/1200_AUS-research/Fabric-TEXT/2_OTST551-2_Hebrew/BOL_exercises/', toFile='BHSa4c_BOL_morphology_prefixingW4a_exercises.tsv')

Hebrew_PrefixingW4a=pd.read_csv('/Users/oliverglanz/Library/CloudStorage/OneDrive-AndrewsUniversity/1200_AUS-research/Fabric-TEXT/2_OTST551-2_Hebrew/BOL_exercises/BHSa4c_BOL_morphology_prefixingW4a_exercises.tsv', delimiter='\t', encoding='utf-16')
Hebrew_PrefixingW4a.head()

## A first attempt to organize and sample the data
## We use `groupby`, a sequence of `sort_values`, and `nth` (to select only 2 entries per grouped category)

Hebrew_PrefixingW4aselection=Hebrew_PrefixingW4a \
                                    .groupby(['TEXT2']) \
                                    .sample(n=5, replace=True)\
                                    .sort_values(['TEXT2','bol_monad_num2'], 
                                                 ascending=True)
Hebrew_PrefixingW4aselection.head(10)

Hebrew_PrefixingW4aselection.to_excel('/Users/oliverglanz/Library/CloudStorage/OneDrive-AndrewsUniversity/1200_AUS-research/Fabric-TEXT/2_OTST551-2_Hebrew/BOL_exercises/BHSa4c_BOL_Hebrew_morphology_PrefixingW4aselection.xlsx', encoding='utf-16')

Hebrew_PrefixingW4b='''
c:clause
 w1:word lex=W g_word~^WA-  bol_dict_HebArm* number* freq_occ* rank_occ* freq_lex bol_dict_abc* language=Hebrew bol_monad_num
 w2:word g_word~^[>HX<]:A[>BGDHWZXVJKLMNS<PYQRFCT][AIOUE@] sp=subs|nmpr bol_monad_num

w1 <: w2


'''
Hebrew_PrefixingW4b  = BHSa4c.search(Hebrew_PrefixingW4b)
BHSa4c.table(Hebrew_PrefixingW4b, start=1, end=50, condensed=False, colorMap={1: 'cyan'})

BHSa4c.export(Hebrew_PrefixingW4b, toDir='/Users/oliverglanz/Library/CloudStorage/OneDrive-AndrewsUniversity/1200_AUS-research/Fabric-TEXT/2_OTST551-2_Hebrew/BOL_exercises/', toFile='BHSa4c_BOL_morphology_prefixingW4b_exercises.tsv')

Hebrew_PrefixingW4b=pd.read_csv('/Users/oliverglanz/Library/CloudStorage/OneDrive-AndrewsUniversity/1200_AUS-research/Fabric-TEXT/2_OTST551-2_Hebrew/BOL_exercises/BHSa4c_BOL_morphology_prefixingW4b_exercises.tsv', delimiter='\t', encoding='utf-16')
Hebrew_PrefixingW4b.head()

## A first attempt to organize and sample the data
## We use `groupby`, a sequence of `sort_values`, and `nth` (to select only 2 entries per grouped category)

Hebrew_PrefixingW4bselection=Hebrew_PrefixingW4b \
                                    .groupby(['TEXT2']) \
                                    .sample(n=5, replace=True)\
                                    .sort_values(['TEXT2','bol_monad_num2'], 
                                                 ascending=True)
Hebrew_PrefixingW4bselection.head(10)

Hebrew_PrefixingW4bselection.to_excel('/Users/oliverglanz/Library/CloudStorage/OneDrive-AndrewsUniversity/1200_AUS-research/Fabric-TEXT/2_OTST551-2_Hebrew/BOL_exercises/BHSa4c_BOL_Hebrew_morphology_PrefixingW4bselection.xlsx', encoding='utf-16')

Hebrew_PrefixingW4c='''
c:clause
 w1:word lex=W g_word~^WE-  bol_dict_HebArm* number* freq_occ* rank_occ* freq_lex bol_dict_abc* language=Hebrew bol_monad_num
 w2:word g_word~^[>HX<]:E[>BGDHWZXVJKLMNS<PYQRFCT][AIOUE@] sp=subs|nmpr

w1 <: w2


'''
Hebrew_PrefixingW4c  = BHSa4c.search(Hebrew_PrefixingW4c)
BHSa4c.table(Hebrew_PrefixingW4c, start=1, end=50, condensed=False, colorMap={1: 'cyan'})

BHSa4c.export(Hebrew_PrefixingW4c, toDir='/Users/oliverglanz/Library/CloudStorage/OneDrive-AndrewsUniversity/1200_AUS-research/Fabric-TEXT/2_OTST551-2_Hebrew/BOL_exercises/', toFile='BHSa4c_BOL_morphology_prefixingW4c_exercises.tsv')

Hebrew_PrefixingW4c=pd.read_csv('/Users/oliverglanz/Library/CloudStorage/OneDrive-AndrewsUniversity/1200_AUS-research/Fabric-TEXT/2_OTST551-2_Hebrew/BOL_exercises/BHSa4c_BOL_morphology_prefixingW4c_exercises.tsv', delimiter='\t', encoding='utf-16')
Hebrew_PrefixingW4c.head()

## A first attempt to organize and sample the data
## We use `groupby`, a sequence of `sort_values`, and `nth` (to select only 2 entries per grouped category)

Hebrew_PrefixingW4cselection=Hebrew_PrefixingW4c \
                                    .groupby(['TEXT2']) \
                                    .sample(n=5, replace=True)\
                                    .sort_values(['TEXT2','bol_monad_num2'], 
                                                 ascending=True)
Hebrew_PrefixingW4cselection.head(10)

Hebrew_PrefixingW4cselection.to_excel('/Users/oliverglanz/Library/CloudStorage/OneDrive-AndrewsUniversity/1200_AUS-research/Fabric-TEXT/2_OTST551-2_Hebrew/BOL_exercises/BHSa4c_BOL_Hebrew_morphology_PrefixingW4cselection.xlsx', encoding='utf-16')

Hebrew_PrefixingW5='''
c:clause
 w1:word lex=W g_word~^W@-    bol_dict_HebArm* number* freq_occ* rank_occ* freq_lex bol_dict_abc* language=Hebrew bol_monad_num
 w2:word g_word~^[>BGDHWZXVJKLMNS<PYQRFCT][AEIOU][0-9][0-9][>BGDHWZXVJKLMNS<PYQRFCT] sp=subs|nmpr bol_monad_num
 

w1 <: w2


'''
Hebrew_PrefixingW5  = BHSa4c.search(Hebrew_PrefixingW5)
BHSa4c.table(Hebrew_PrefixingW5, start=1, end=50, condensed=False, colorMap={1: 'cyan'})

BHSa4c.export(Hebrew_PrefixingW5, toDir='/Users/oliverglanz/Library/CloudStorage/OneDrive-AndrewsUniversity/1200_AUS-research/Fabric-TEXT/2_OTST551-2_Hebrew/BOL_exercises/', toFile='BHSa4c_BOL_morphology_prefixingW5_exercises.tsv')

Hebrew_PrefixingW5=pd.read_csv('/Users/oliverglanz/Library/CloudStorage/OneDrive-AndrewsUniversity/1200_AUS-research/Fabric-TEXT/2_OTST551-2_Hebrew/BOL_exercises/BHSa4c_BOL_morphology_prefixingW5_exercises.tsv', delimiter='\t', encoding='utf-16')
Hebrew_PrefixingW5.head()

## A first attempt to organize and sample the data
## We use `groupby`, a sequence of `sort_values`, and `nth` (to select only 2 entries per grouped category)

Hebrew_PrefixingW5selection=Hebrew_PrefixingW5 \
                                    .groupby(['TEXT2']) \
                                    .sample(n=5, replace=True)\
                                    .sort_values(['TEXT2','bol_monad_num2'], 
                                                 ascending=True)
Hebrew_PrefixingW5selection.head(10)

Hebrew_PrefixingW5selection.to_excel('/Users/oliverglanz/Library/CloudStorage/OneDrive-AndrewsUniversity/1200_AUS-research/Fabric-TEXT/2_OTST551-2_Hebrew/BOL_exercises/BHSa4c_BOL_Hebrew_morphology_PrefixingW5selection.xlsx', encoding='utf-16')

Hebrew_Prefixing_Research1='''
c:clause
 w1:word lex=W g_word~^WI     bol_dict_HebArm* number* freq_occ* rank_occ* freq_lex bol_dict_abc* language=Hebrew bol_monad_num
 w2:word lex~^J g_word~^J g_lex~^J sp=subs

w1 <: w2


'''
Hebrew_Prefixing_Research1  = BHSa4c.search(Hebrew_Prefixing_Research1)
BHSa4c.table(Hebrew_Prefixing_Research1, start=1, end=50, condensed=False, colorMap={1: 'cyan'})

Hebrew_Prefixing_Research2='''
clause 
 w1:word lex=W g_word~^WI.*     bol_dict_HebArm* number* freq_occ* rank_occ* freq_lex bol_dict_abc* language=Hebrew bol_monad_num
 w2:word lex~^J g_word~^J g_lex~^J sp=nmpr|subs lex#JHWH/

w1 <: w2



'''
Hebrew_Prefixing_Research2  = BHSa4c.search(Hebrew_Prefixing_Research2)
BHSa4c.table(Hebrew_Prefixing_Research2, start=1, end=50, condensed=False, colorMap={1: 'cyan'})

Hebrew_PrefixingBKL1='''
c:phrase
 w1:word lex=B|K|L g_word~^B.I-|^K.I-|^LI-     bol_dict_HebArm* number* freq_occ* rank_occ* freq_lex bol_dict_abc* language=Hebrew bol_monad_num
 w2:word g_word~^[>BGDHWZXVKLMNS<PYQRFCT]:[>BGDHWZXVJKLMNS<PYQRFCT][AIOUE@] sp=subs|nmpr bol_monad_num

w1 <: w2


'''
Hebrew_PrefixingBKL1  = BHSa4c.search(Hebrew_PrefixingBKL1)
BHSa4c.table(Hebrew_PrefixingBKL1, start=1, end=10, condensed=False, colorMap={1: 'cyan'})

BHSa4c.export(Hebrew_PrefixingBKL1, toDir='/Users/oliverglanz/Library/CloudStorage/OneDrive-AndrewsUniversity/1200_AUS-research/Fabric-TEXT/2_OTST551-2_Hebrew/BOL_exercises/', toFile='BHSa4c_BOL_morphology_prefixingBKL1_exercises.tsv')

Hebrew_PrefixingBKL1=pd.read_csv('/Users/oliverglanz/Library/CloudStorage/OneDrive-AndrewsUniversity/1200_AUS-research/Fabric-TEXT/2_OTST551-2_Hebrew/BOL_exercises/BHSa4c_BOL_morphology_prefixingBKL1_exercises.tsv', delimiter='\t', encoding='utf-16')
Hebrew_PrefixingBKL1.head()

## A first attempt to organize and sample the data
## We use `groupby`, a sequence of `sort_values`, and `nth` (to select only 2 entries per grouped category)

Hebrew_PrefixingBKL1selection=Hebrew_PrefixingBKL1 \
                                    .groupby(['TEXT2']) \
                                    .sample(n=5, replace=True)\
                                    .sort_values(['TEXT2','bol_monad_num2'], 
                                                 ascending=True)
Hebrew_PrefixingBKL1selection.head(10)

Hebrew_PrefixingBKL1selection.to_excel('/Users/oliverglanz/Library/CloudStorage/OneDrive-AndrewsUniversity/1200_AUS-research/Fabric-TEXT/2_OTST551-2_Hebrew/BOL_exercises/BHSa4c_BOL_Hebrew_morphology_PrefixingBKL1selection.xlsx', encoding='utf-16')

Hebrew_PrefixingBKL2='''
c:phrase
 w1:word lex=B|K|L g_word~^B.I-|^K.I-|^LI-     bol_dict_HebArm* number* freq_occ* rank_occ* freq_lex bol_dict_abc* language=Hebrew bol_monad_num
 w2:word g_lex~J g_word~^J[>BGDHWZXVJKLMNS<PYQRFCT] sp=subs|nmpr bol_monad_num

w1 <: w2


'''
Hebrew_PrefixingBKL2  = BHSa4c.search(Hebrew_PrefixingBKL2)
BHSa4c.table(Hebrew_PrefixingBKL2, start=1, end=10, condensed=False, colorMap={1: 'cyan'})

BHSa4c.export(Hebrew_PrefixingBKL2, toDir='/Users/oliverglanz/Library/CloudStorage/OneDrive-AndrewsUniversity/1200_AUS-research/Fabric-TEXT/2_OTST551-2_Hebrew/BOL_exercises/', toFile='BHSa4c_BOL_morphology_prefixingBKL2_exercises.tsv')

Hebrew_PrefixingBKL2=pd.read_csv('/Users/oliverglanz/Library/CloudStorage/OneDrive-AndrewsUniversity/1200_AUS-research/Fabric-TEXT/2_OTST551-2_Hebrew/BOL_exercises/BHSa4c_BOL_morphology_prefixingBKL2_exercises.tsv', delimiter='\t', encoding='utf-16')
Hebrew_PrefixingBKL2.head()

## A first attempt to organize and sample the data
## We use `groupby`, a sequence of `sort_values`, and `nth` (to select only 2 entries per grouped category)

Hebrew_PrefixingBKL2selection=Hebrew_PrefixingBKL2 \
                                    .groupby(['TEXT2']) \
                                    .sample(n=5, replace=True)\
                                    .sort_values(['TEXT2','bol_monad_num2'], 
                                                 ascending=True)
Hebrew_PrefixingBKL2selection.head(10)

Hebrew_PrefixingBKL2selection.to_excel('/Users/oliverglanz/Library/CloudStorage/OneDrive-AndrewsUniversity/1200_AUS-research/Fabric-TEXT/2_OTST551-2_Hebrew/BOL_exercises/BHSa4c_BOL_Hebrew_morphology_PrefixingBKL2selection.xlsx', encoding='utf-16')

Hebrew_PrefixingBKL3a='''
c:clause
 w1:word lex=B|K|L g_word~^B.@-|^K.@-|^L@- bol_dict_HebArm* number* freq_occ* rank_occ* freq_lex bol_dict_abc* language=Hebrew bol_monad_num
 w2:word g_word~^[>HX<]:@[>BGDHWZXVJKLMNS<PYQRFCT] sp=subs|nmpr bol_monad_num

w1 <: w2


'''
Hebrew_PrefixingBKL3a  = BHSa4c.search(Hebrew_PrefixingBKL3a)
BHSa4c.table(Hebrew_PrefixingBKL3a, start=1, end=50, condensed=False, colorMap={1: 'cyan'})

BHSa4c.export(Hebrew_PrefixingBKL3a, toDir='/Users/oliverglanz/Library/CloudStorage/OneDrive-AndrewsUniversity/1200_AUS-research/Fabric-TEXT/2_OTST551-2_Hebrew/BOL_exercises', toFile='BHSa4c_BOL_morphology_prefixingBKL3a_exercises.tsv')

Hebrew_PrefixingBKL3a=pd.read_csv('/Users/oliverglanz/Library/CloudStorage/OneDrive-AndrewsUniversity/1200_AUS-research/Fabric-TEXT/2_OTST551-2_Hebrew/BOL_exercises/BHSa4c_BOL_morphology_prefixingBKL3a_exercises.tsv', delimiter='\t', encoding='utf-16')
Hebrew_PrefixingBKL3a.head()

## A first attempt to organize and sample the data
## We use `groupby`, a sequence of `sort_values`, and `nth` (to select only 2 entries per grouped category)

Hebrew_PrefixingBKL3aselection=Hebrew_PrefixingBKL3a \
                                    .groupby(['TEXT2']) \
                                    .sample(n=5, replace=True)\
                                    .sort_values(['TEXT2','bol_monad_num2'], 
                                                 ascending=True)
Hebrew_PrefixingBKL3aselection.head(10)

Hebrew_PrefixingBKL3aselection.to_excel('/Users/oliverglanz/Library/CloudStorage/OneDrive-AndrewsUniversity/1200_AUS-research/Fabric-TEXT/2_OTST551-2_Hebrew/BOL_exercises/BHSa4c_BOL_Hebrew_morphology_PrefixingBKL3aselection.xlsx', encoding='utf-16')

Hebrew_PrefixingBKL3b='''
c:clause
 w1:word lex=B|K|L g_word~^B.A-|^K.A-|^LA- bol_dict_HebArm* number* freq_occ* rank_occ* freq_lex bol_dict_abc* language=Hebrew bol_monad_num
 w2:word g_word~^[>HX<]:A[>BGDHWZXVJKLMNS<PYQRFCT] sp=subs|nmpr bol_monad_num

w1 <: w2


'''
Hebrew_PrefixingBKL3b  = BHSa4c.search(Hebrew_PrefixingBKL3b)
BHSa4c.table(Hebrew_PrefixingBKL3b, start=1, end=50, condensed=False, colorMap={1: 'cyan'})

BHSa4c.export(Hebrew_PrefixingBKL3b, toDir='/Users/oliverglanz/Library/CloudStorage/OneDrive-AndrewsUniversity/1200_AUS-research/Fabric-TEXT/2_OTST551-2_Hebrew/BOL_exercises/', toFile='BHSa4c_BOL_morphology_prefixingBKL3b_exercises.tsv')

Hebrew_PrefixingBKL3b=pd.read_csv('/Users/oliverglanz/Library/CloudStorage/OneDrive-AndrewsUniversity/1200_AUS-research/Fabric-TEXT/2_OTST551-2_Hebrew/BOL_exercises/BHSa4c_BOL_morphology_prefixingBKL3b_exercises.tsv', delimiter='\t', encoding='utf-16')
Hebrew_PrefixingBKL3b.head()

## A first attempt to organize and sample the data
## We use `groupby`, a sequence of `sort_values`, and `nth` (to select only 2 entries per grouped category)

Hebrew_PrefixingBKL3bselection=Hebrew_PrefixingBKL3b \
                                    .groupby(['TEXT2']) \
                                    .sample(n=5, replace=True)\
                                    .sort_values(['TEXT2','bol_monad_num2'], 
                                                 ascending=True)
Hebrew_PrefixingBKL3bselection.head(10)

Hebrew_PrefixingBKL3bselection.to_excel('/Users/oliverglanz/Library/CloudStorage/OneDrive-AndrewsUniversity/1200_AUS-research/Fabric-TEXT/2_OTST551-2_Hebrew/BOL_exercises/BHSa4c_BOL_Hebrew_morphology_PrefixingBKL3bselection.xlsx', encoding='utf-16')

Hebrew_PrefixingBKL3c='''
c:clause
 w1:word lex=B|K|L g_word~^B.E-|^K.E-|^LE- bol_dict_HebArm* number* freq_occ* rank_occ* freq_lex bol_dict_abc* language=Hebrew bol_monad_num
 w2:word g_word~^[>HX<]:E[>BGDHWZXVJKLMNS<PYQRFCT] sp=subs|nmpr bol_monad_num

w1 <: w2


'''
Hebrew_PrefixingBKL3c  = BHSa4c.search(Hebrew_PrefixingBKL3c)
BHSa4c.table(Hebrew_PrefixingBKL3c, start=1, end=50, condensed=False, colorMap={1: 'cyan'})

BHSa4c.export(Hebrew_PrefixingBKL3c, toDir='/Users/oliverglanz/Library/CloudStorage/OneDrive-AndrewsUniversity/1200_AUS-research/Fabric-TEXT/2_OTST551-2_Hebrew/BOL_exercises/', toFile='BHSa4c_BOL_morphology_prefixingBKL3c_exercises.tsv')

Hebrew_PrefixingBKL3c=pd.read_csv('/Users/oliverglanz/Library/CloudStorage/OneDrive-AndrewsUniversity/1200_AUS-research/Fabric-TEXT/2_OTST551-2_Hebrew/BOL_exercises/BHSa4c_BOL_morphology_prefixingBKL3c_exercises.tsv', delimiter='\t', encoding='utf-16')
Hebrew_PrefixingBKL3c.head()

## A first attempt to organize and sample the data
## We use `groupby`, a sequence of `sort_values`, and `nth` (to select only 2 entries per grouped category)

Hebrew_PrefixingBKL3cselection=Hebrew_PrefixingBKL3c \
                                    .groupby(['TEXT2']) \
                                    .sample(n=5, replace=True)\
                                    .sort_values(['TEXT2','bol_monad_num2'], 
                                                 ascending=True)
Hebrew_PrefixingBKL3cselection.head(10)

Hebrew_PrefixingBKL3cselection.to_excel('/Users/oliverglanz/Library/CloudStorage/OneDrive-AndrewsUniversity/1200_AUS-research/Fabric-TEXT/2_OTST551-2_Hebrew/BOL_exercises/BHSa4c_BOL_Hebrew_morphology_PrefixingBKL3cselection.xlsx', encoding='utf-16')

Hebrew_PrefixingBKL4='''
c:clause
 w1:word lex=B|K|L g_word~^B.@-|^K.@-|^L@-    bol_dict_HebArm* number* freq_occ* rank_occ* freq_lex bol_dict_abc* language=Hebrew bol_monad_num
 w2:word g_word~^[>BGDHWZXVJKLMNS<PYQRFCT][AEIOU][0-9][0-9][>BGDHWZXVJKLMNS<PYQRFCT] sp=subs|nmpr bol_monad_num

w1 <: w2


'''
Hebrew_PrefixingBKL4  = BHSa4c.search(Hebrew_PrefixingBKL4)
BHSa4c.table(Hebrew_PrefixingBKL4, start=1, end=50, condensed=False, colorMap={1: 'cyan'})

BHSa4c.export(Hebrew_PrefixingBKL4, toDir='/Users/oliverglanz/Library/CloudStorage/OneDrive-AndrewsUniversity/1200_AUS-research/Fabric-TEXT/2_OTST551-2_Hebrew/BOL_exercises/', toFile='BHSa4c_BOL_morphology_prefixingBKL4_exercises.tsv')

Hebrew_PrefixingBKL4=pd.read_csv('/Users/oliverglanz/Library/CloudStorage/OneDrive-AndrewsUniversity/1200_AUS-research/Fabric-TEXT/2_OTST551-2_Hebrew/BOL_exercises/BHSa4c_BOL_morphology_prefixingBKL4_exercises.tsv', delimiter='\t', encoding='utf-16')
Hebrew_PrefixingBKL4.head()

## A first attempt to organize and sample the data
## We use `groupby`, a sequence of `sort_values`, and `nth` (to select only 2 entries per grouped category)

Hebrew_PrefixingBKL4selection=Hebrew_PrefixingBKL4 \
                                    .groupby(['TEXT2']) \
                                    .sample(n=5, replace=True)\
                                    .sort_values(['TEXT2','bol_monad_num2'], 
                                                 ascending=True)
Hebrew_PrefixingBKL4selection.head(10)

Hebrew_PrefixingBKL4selection.to_excel('/Users/oliverglanz/Library/CloudStorage/OneDrive-AndrewsUniversity/1200_AUS-research/Fabric-TEXT/2_OTST551-2_Hebrew/BOL_exercises/BHSa4c_BOL_Hebrew_morphology_PrefixingBKL4selection.xlsx', encoding='utf-16')

Hebrew_PrefixingMN1='''
c:clause
 w1:word lex=MN g_word~^MI-    bol_dict_HebArm* number* freq_occ* rank_occ* freq_lex bol_dict_abc* language=Hebrew bol_monad_num
 w2:word g_word~^[BGDWZVJKLMNSPYQFCT] sp=subs|nmpr bol_monad_num

w1 <: w2


'''
Hebrew_PrefixingMN1  = BHSa4c.search(Hebrew_PrefixingMN1)
BHSa4c.table(Hebrew_PrefixingMN1, start=1, end=50, condensed=False, colorMap={1: 'cyan'})

BHSa4c.export(Hebrew_PrefixingMN1, toDir='/Users/oliverglanz/Library/CloudStorage/OneDrive-AndrewsUniversity/1200_AUS-research/Fabric-TEXT/2_OTST551-2_Hebrew/BOL_exercises/', toFile='BHSa4c_BOL_morphology_prefixingMN1_exercises.tsv')

Hebrew_PrefixingMN1=pd.read_csv('/Users/oliverglanz/Library/CloudStorage/OneDrive-AndrewsUniversity/1200_AUS-research/Fabric-TEXT/2_OTST551-2_Hebrew/BOL_exercises/BHSa4c_BOL_morphology_prefixingMN1_exercises.tsv', delimiter='\t', encoding='utf-16')
Hebrew_PrefixingMN1.head()

## A first attempt to organize and sample the data
## We use `groupby`, a sequence of `sort_values`, and `nth` (to select only 2 entries per grouped category)

Hebrew_PrefixingMN1selection=Hebrew_PrefixingMN1 \
                                    .groupby(['TEXT2']) \
                                    .sample(n=5, replace=True)\
                                    .sort_values(['TEXT2','bol_monad_num2'], 
                                                 ascending=True)
Hebrew_PrefixingMN1selection.head(10)

Hebrew_PrefixingMN1selection.to_excel('/Users/oliverglanz/Library/CloudStorage/OneDrive-AndrewsUniversity/1200_AUS-research/Fabric-TEXT/2_OTST551-2_Hebrew/BOL_exercises/BHSa4c_BOL_Hebrew_morphology_PrefixingMN1selection.xlsx', encoding='utf-16')

Hebrew_PrefixingMN2='''
c:clause
 w1:word lex=MN g_word~^M;-    bol_dict_HebArm* number* freq_occ* rank_occ* freq_lex bol_dict_abc* language=Hebrew bol_monad_num
 w2:word g_word~^[>HX<] sp=subs|nmpr bol_monad_num

w1 <: w2


'''
Hebrew_PrefixingMN2  = BHSa4c.search(Hebrew_PrefixingMN2)
BHSa4c.table(Hebrew_PrefixingMN2, start=1, end=50, condensed=False, colorMap={1: 'cyan'})

BHSa4c.export(Hebrew_PrefixingMN2, toDir='/Users/oliverglanz/Library/CloudStorage/OneDrive-AndrewsUniversity/1200_AUS-research/Fabric-TEXT/2_OTST551-2_Hebrew/BOL_exercises/', toFile='BHSa4c_BOL_morphology_prefixingMN2_exercises.tsv')

Hebrew_PrefixingMN2=pd.read_csv('/Users/oliverglanz/Library/CloudStorage/OneDrive-AndrewsUniversity/1200_AUS-research/Fabric-TEXT/2_OTST551-2_Hebrew/BOL_exercises/BHSa4c_BOL_morphology_prefixingMN2_exercises.tsv', delimiter='\t', encoding='utf-16')
Hebrew_PrefixingMN2.head()

## A first attempt to organize and sample the data
## We use `groupby`, a sequence of `sort_values`, and `nth` (to select only 2 entries per grouped category)

Hebrew_PrefixingMN2selection=Hebrew_PrefixingMN2 \
                                    .groupby(['TEXT2']) \
                                    .sample(n=5, replace=True)\
                                    .sort_values(['TEXT2','bol_monad_num2'], 
                                                 ascending=True)
Hebrew_PrefixingMN2selection.head(10)

Hebrew_PrefixingMN2selection.to_excel('/Users/oliverglanz/Library/CloudStorage/OneDrive-AndrewsUniversity/1200_AUS-research/Fabric-TEXT/2_OTST551-2_Hebrew/BOL_exercises/BHSa4c_BOL_Hebrew_morphology_PrefixingMN2selection.xlsx', encoding='utf-16')

Hebrew_PrefixingH1='''
c:clause
 w1:word lex=H g_word~^HA-    bol_dict_HebArm* number* freq_occ* rank_occ* freq_lex bol_dict_abc* language=Hebrew bol_monad_num
 w2:word g_word~^[BGDWZVJKLMNSPYQFCT] sp=subs|nmpr bol_monad_num

w1 <: w2


'''
Hebrew_PrefixingH1  = BHSa4c.search(Hebrew_PrefixingH1)
BHSa4c.table(Hebrew_PrefixingH1, start=1, end=50, condensed=False, colorMap={1: 'cyan'})

BHSa4c.export(Hebrew_PrefixingH1, toDir='/Users/oliverglanz/Library/CloudStorage/OneDrive-AndrewsUniversity/1200_AUS-research/Fabric-TEXT/2_OTST551-2_Hebrew/BOL_exercises/', toFile='BHSa4c_BOL_morphology_prefixingH1_exercises.tsv')

Hebrew_PrefixingH1=pd.read_csv('/Users/oliverglanz/Library/CloudStorage/OneDrive-AndrewsUniversity/1200_AUS-research/Fabric-TEXT/2_OTST551-2_Hebrew/BOL_exercises/BHSa4c_BOL_morphology_prefixingH1_exercises.tsv', delimiter='\t', encoding='utf-16')
Hebrew_PrefixingH1.head()

## A first attempt to organize and sample the data
## We use `groupby`, a sequence of `sort_values`, and `nth` (to select only 2 entries per grouped category)

Hebrew_PrefixingH1selection=Hebrew_PrefixingH1 \
                                    .groupby(['TEXT2']) \
                                    .sample(n=5, replace=True)\
                                    .sort_values(['TEXT2','bol_monad_num2'], 
                                                 ascending=True)
Hebrew_PrefixingH1selection.head(10)

Hebrew_PrefixingH1selection.to_excel('/Users/oliverglanz/Library/CloudStorage/OneDrive-AndrewsUniversity/1200_AUS-research/Fabric-TEXT/2_OTST551-2_Hebrew/BOL_exercises/BHSa4c_BOL_Hebrew_morphology_PrefixingH1selection.xlsx', encoding='utf-16')

Hebrew_PrefixingH2='''
c:clause
 w1:word lex=H g_word~^H@-    bol_dict_HebArm* number* freq_occ* rank_occ* freq_lex bol_dict_abc* language=Hebrew bol_monad_num
 w2:word g_word~^[><R] sp=subs|nmpr bol_monad_num

w1 <: w2


'''
Hebrew_PrefixingH2  = BHSa4c.search(Hebrew_PrefixingH2)
BHSa4c.table(Hebrew_PrefixingH2, start=1, end=50, condensed=False, colorMap={1: 'cyan'})

BHSa4c.export(Hebrew_PrefixingH2, toDir='/Users/oliverglanz/Library/CloudStorage/OneDrive-AndrewsUniversity/1200_AUS-research/Fabric-TEXT/2_OTST551-2_Hebrew/BOL_exercises/', toFile='BHSa4c_BOL_morphology_prefixingH2_exercises.tsv')

Hebrew_PrefixingH2=pd.read_csv('/Users/oliverglanz/Library/CloudStorage/OneDrive-AndrewsUniversity/1200_AUS-research/Fabric-TEXT/2_OTST551-2_Hebrew/BOL_exercises/BHSa4c_BOL_morphology_prefixingH2_exercises.tsv', delimiter='\t', encoding='utf-16')
Hebrew_PrefixingH2.head()

## A first attempt to organize and sample the data
## We use `groupby`, a sequence of `sort_values`, and `nth` (to select only 2 entries per grouped category)

Hebrew_PrefixingH2selection=Hebrew_PrefixingH2 \
                                    .groupby(['TEXT2']) \
                                    .sample(n=5, replace=True)\
                                    .sort_values(['TEXT2','bol_monad_num2'], 
                                                 ascending=True)
Hebrew_PrefixingH2selection.head(10)

Hebrew_PrefixingH2selection.to_excel('/Users/oliverglanz/Library/CloudStorage/OneDrive-AndrewsUniversity/1200_AUS-research/Fabric-TEXT/2_OTST551-2_Hebrew/BOL_exercises/BHSa4c_BOL_Hebrew_morphology_PrefixingH2selection.xlsx', encoding='utf-16')

Hebrew_PrefixingH3='''
c:clause
 w1:word lex=H g_word~^HA-    bol_dict_HebArm* number* freq_occ* rank_occ* freq_lex bol_dict_abc* language=Hebrew bol_monad_num
 w2:word g_word~^[HX][AEIOU] sp=subs|nmpr bol_monad_num

w1 <: w2


'''
Hebrew_PrefixingH3  = BHSa4c.search(Hebrew_PrefixingH3)
BHSa4c.table(Hebrew_PrefixingH3, start=1, end=50, condensed=False, colorMap={1: 'cyan'})

BHSa4c.export(Hebrew_PrefixingH3, toDir='/Users/oliverglanz/Library/CloudStorage/OneDrive-AndrewsUniversity/1200_AUS-research/Fabric-TEXT/2_OTST551-2_Hebrew/BOL_exercises/', toFile='BHSa4c_BOL_morphology_prefixingH3_exercises.tsv')

Hebrew_PrefixingH3=pd.read_csv('/Users/oliverglanz/Library/CloudStorage/OneDrive-AndrewsUniversity/1200_AUS-research/Fabric-TEXT/2_OTST551-2_Hebrew/BOL_exercises/BHSa4c_BOL_morphology_prefixingH3_exercises.tsv', delimiter='\t', encoding='utf-16')
Hebrew_PrefixingH3.head()

## A first attempt to organize and sample the data
## We use `groupby`, a sequence of `sort_values`, and `nth` (to select only 2 entries per grouped category)

Hebrew_PrefixingH3selection=Hebrew_PrefixingH3 \
                                    .groupby(['TEXT2']) \
                                    .sample(n=5, replace=True)\
                                    .sort_values(['TEXT2','bol_monad_num2'], 
                                                 ascending=True)
Hebrew_PrefixingH3selection.head(10)

Hebrew_PrefixingH3selection.to_excel('/Users/oliverglanz/Library/CloudStorage/OneDrive-AndrewsUniversity/1200_AUS-research/Fabric-TEXT/2_OTST551-2_Hebrew/BOL_exercises/BHSa4c_BOL_Hebrew_morphology_PrefixingH3selection.xlsx', encoding='utf-16')

Hebrew_PrefixingH4='''
c:clause
 w1:word lex=H g_word~^HE-    bol_dict_HebArm* number* freq_occ* rank_occ* freq_lex bol_dict_abc* language=Hebrew bol_monad_num
 w2:word g_word~^[HX][@] sp=subs|nmpr bol_monad_num

w1 <: w2


'''
Hebrew_PrefixingH4  = BHSa4c.search(Hebrew_PrefixingH4)
BHSa4c.table(Hebrew_PrefixingH4, start=1, end=50, condensed=False, colorMap={1: 'cyan'})

BHSa4c.export(Hebrew_PrefixingH4, toDir='/Users/oliverglanz/Library/CloudStorage/OneDrive-AndrewsUniversity/1200_AUS-research/Fabric-TEXT/2_OTST551-2_Hebrew/BOL_exercises/', toFile='BHSa4c_BOL_morphology_prefixingH4_exercises.tsv')

Hebrew_PrefixingH4=pd.read_csv('/Users/oliverglanz/Library/CloudStorage/OneDrive-AndrewsUniversity/1200_AUS-research/Fabric-TEXT/2_OTST551-2_Hebrew/BOL_exercises/BHSa4c_BOL_morphology_prefixingH4_exercises.tsv', delimiter='\t', encoding='utf-16')
Hebrew_PrefixingH4.head()

## A first attempt to organize and sample the data
## We use `groupby`, a sequence of `sort_values`, and `nth` (to select only 2 entries per grouped category)

Hebrew_PrefixingH4selection=Hebrew_PrefixingH4 \
                                    .groupby(['TEXT2']) \
                                    .sample(n=5, replace=True)\
                                    .sort_values(['TEXT2','bol_monad_num2'], 
                                                 ascending=True)
Hebrew_PrefixingH4selection.head(10)

Hebrew_PrefixingH4selection.to_excel('/Users/oliverglanz/Library/CloudStorage/OneDrive-AndrewsUniversity/1200_AUS-research/Fabric-TEXT/2_OTST551-2_Hebrew/BOL_exercises/BHSa4c_BOL_Hebrew_morphology_PrefixingH4selection.xlsx', encoding='utf-16')

Hebrew_PrefixingBKLH1='''
c:clause
 w1:word lex=B|K|L g_word~^B.A-|K.A-|LA-    bol_dict_HebArm* number* freq_occ* rank_occ* freq_lex bol_dict_abc* language=Hebrew bol_monad_num
 w2:word lex=H g_word~^-    bol_dict_HebArm* number* freq_occ* rank_occ* freq_lex bol_dict_abc* language=Hebrew bol_monad_num
 w3:word g_word~^[BGDWZVJKLMNSPYQFCT] sp=subs|nmpr lex  bol_monad_num

w1 <: w2
w2 <: w3


'''
Hebrew_PrefixingBKLH1  = BHSa4c.search(Hebrew_PrefixingBKLH1)
BHSa4c.table(Hebrew_PrefixingBKLH1, start=1, end=50, condensed=False, colorMap={1: 'cyan'})

BHSa4c.export(Hebrew_PrefixingBKLH1, toDir='/Users/oliverglanz/Library/CloudStorage/OneDrive-AndrewsUniversity/1200_AUS-research/Fabric-TEXT/2_OTST551-2_Hebrew/BOL_exercises/', toFile='BHSa4c_BOL_morphology_prefixingBKLH1_exercises.tsv')

Hebrew_PrefixingBKLH1=pd.read_csv('/Users/oliverglanz/Library/CloudStorage/OneDrive-AndrewsUniversity/1200_AUS-research/Fabric-TEXT/2_OTST551-2_Hebrew/BOL_exercises/BHSa4c_BOL_morphology_prefixingBKLH1_exercises.tsv', delimiter='\t', encoding='utf-16')
Hebrew_PrefixingBKLH1.head()

## A first attempt to organize and sample the data
## We use `groupby`, a sequence of `sort_values`, and `nth` (to select only 2 entries per grouped category)

Hebrew_PrefixingBKLH1selection=Hebrew_PrefixingBKLH1 \
                                    .groupby(['TEXT2']) \
                                    .sample(n=5, replace=True)\
                                    .sort_values(['TEXT2','bol_monad_num2'], 
                                                 ascending=True)
Hebrew_PrefixingBKLH1selection.head(10)

Hebrew_PrefixingBKLH1selection.to_excel('/Users/oliverglanz/Library/CloudStorage/OneDrive-AndrewsUniversity/1200_AUS-research/Fabric-TEXT/2_OTST551-2_Hebrew/BOL_exercises/BHSa4c_BOL_Hebrew_morphology_PrefixingBKLH1selection.xlsx', encoding='utf-16')

Hebrew_PrefixingBKLH2='''
c:clause
 w1:word lex=B|K|L g_word~^B.@-|K.@-|L@-    bol_dict_HebArm* number* freq_occ* rank_occ* freq_lex bol_dict_abc* language=Hebrew bol_monad_num
 w2:word lex=H g_word~^-    bol_dict_HebArm* number* freq_occ* rank_occ* freq_lex bol_dict_abc* language=Hebrew bol_monad_num
 w3:word g_word~^[><R] sp=subs|nmpr bol_monad_num

w1 <: w2
w2 <: w3


'''
Hebrew_PrefixingBKLH2  = BHSa4c.search(Hebrew_PrefixingBKLH2)
BHSa4c.table(Hebrew_PrefixingBKLH2, start=1, end=50, condensed=False, colorMap={1: 'cyan'})

BHSa4c.export(Hebrew_PrefixingBKLH2, toDir='/Users/oliverglanz/Library/CloudStorage/OneDrive-AndrewsUniversity/1200_AUS-research/Fabric-TEXT/2_OTST551-2_Hebrew/BOL_exercises/', toFile='BHSa4c_BOL_morphology_prefixingBKLH2_exercises.tsv')

Hebrew_PrefixingBKLH2=pd.read_csv('/Users/oliverglanz/Library/CloudStorage/OneDrive-AndrewsUniversity/1200_AUS-research/Fabric-TEXT/2_OTST551-2_Hebrew/BOL_exercises/BHSa4c_BOL_morphology_prefixingBKLH2_exercises.tsv', delimiter='\t', encoding='utf-16')
Hebrew_PrefixingBKLH2.head()

## A first attempt to organize and sample the data
## We use `groupby`, a sequence of `sort_values`, and `nth` (to select only 2 entries per grouped category)

Hebrew_PrefixingBKLH2selection=Hebrew_PrefixingBKLH2 \
                                    .groupby(['TEXT2']) \
                                    .sample(n=5, replace=True)\
                                    .sort_values(['TEXT2','bol_monad_num2'], 
                                                 ascending=True)
Hebrew_PrefixingBKLH2selection.head(10)

Hebrew_PrefixingBKLH2selection.to_excel('/Users/oliverglanz/Library/CloudStorage/OneDrive-AndrewsUniversity/1200_AUS-research/Fabric-TEXT/2_OTST551-2_Hebrew/BOL_exercises/BHSa4c_BOL_Hebrew_morphology_PrefixingBKLH2selection.xlsx', encoding='utf-16')

Hebrew_PrefixingBKLH3='''
c:clause
 w1:word lex=B|K|L g_word~^B.A-|K.A-|LA-    bol_dict_HebArm* number* freq_occ* rank_occ* freq_lex bol_dict_abc* language=Hebrew bol_monad_num
 w2:word lex=H g_word~^-    bol_dict_HebArm* number* freq_occ* rank_occ* freq_lex bol_dict_abc* language=Hebrew bol_monad_num
 w3:word g_word~^[HX][AEIOU] sp=subs|nmpr bol_monad_num

w1 <: w2
w2 <: w3


'''
Hebrew_PrefixingBKLH3  = BHSa4c.search(Hebrew_PrefixingBKLH3)
BHSa4c.table(Hebrew_PrefixingBKLH3, start=1, end=50, condensed=False, colorMap={1: 'cyan'})

BHSa4c.export(Hebrew_PrefixingBKLH3, toDir='/Users/oliverglanz/Library/CloudStorage/OneDrive-AndrewsUniversity/1200_AUS-research/Fabric-TEXT/2_OTST551-2_Hebrew/BOL_exercises/', toFile='BHSa4c_BOL_morphology_prefixingBKLH3_exercises.tsv')

Hebrew_PrefixingBKLH3=pd.read_csv('/Users/oliverglanz/Library/CloudStorage/OneDrive-AndrewsUniversity/1200_AUS-research/Fabric-TEXT/2_OTST551-2_Hebrew/BOL_exercises/BHSa4c_BOL_morphology_prefixingBKLH3_exercises.tsv', delimiter='\t', encoding='utf-16')
Hebrew_PrefixingBKLH3.head()

## A first attempt to organize and sample the data
## We use `groupby`, a sequence of `sort_values`, and `nth` (to select only 2 entries per grouped category)

Hebrew_PrefixingBKLH3selection=Hebrew_PrefixingBKLH3 \
                                    .groupby(['TEXT2']) \
                                    .sample(n=5, replace=True)\
                                    .sort_values(['TEXT2','bol_monad_num2'], 
                                                 ascending=True)
Hebrew_PrefixingBKLH3selection.head(10)

Hebrew_PrefixingBKLH3selection.to_excel('/Users/oliverglanz/Library/CloudStorage/OneDrive-AndrewsUniversity/1200_AUS-research/Fabric-TEXT/2_OTST551-2_Hebrew/BOL_exercises/BHSa4c_BOL_Hebrew_morphology_PrefixingBKLH3selection.xlsx', encoding='utf-16')

Hebrew_PrefixingBKLH4='''
c:clause
 w1:word lex=B|K|L g_word~^B.E-|K.E-|LE-    bol_dict_HebArm* number* freq_occ* rank_occ* freq_lex bol_dict_abc* language=Hebrew bol_monad_num
 w2:word lex=H g_word~^-    bol_dict_HebArm* number* freq_occ* rank_occ* freq_lex bol_dict_abc* language=Hebrew bol_monad_num
 w3:word g_word~^[HX]@ sp=subs|nmpr bol_monad_num

w1 <: w2
w2 <: w3


'''
Hebrew_PrefixingBKLH4  = BHSa4c.search(Hebrew_PrefixingBKLH4)
BHSa4c.table(Hebrew_PrefixingBKLH4, start=1, end=50, condensed=False, colorMap={1: 'cyan'})

BHSa4c.export(Hebrew_PrefixingBKLH4, toDir='/Users/oliverglanz/Library/CloudStorage/OneDrive-AndrewsUniversity/1200_AUS-research/Fabric-TEXT/2_OTST551-2_Hebrew/BOL_exercises/', toFile='BHSa4c_BOL_morphology_prefixingBKLH4_exercises.tsv')

Hebrew_PrefixingBKLH4=pd.read_csv('/Users/oliverglanz/Library/CloudStorage/OneDrive-AndrewsUniversity/1200_AUS-research/Fabric-TEXT/2_OTST551-2_Hebrew/BOL_exercises/BHSa4c_BOL_morphology_prefixingBKLH4_exercises.tsv', delimiter='\t', encoding='utf-16')
Hebrew_PrefixingBKLH4.head()

## A first attempt to organize and sample the data
## We use `groupby`, a sequence of `sort_values`, and `nth` (to select only 2 entries per grouped category)

Hebrew_PrefixingBKLH4selection=Hebrew_PrefixingBKLH4 \
                                    .groupby(['TEXT2']) \
                                    .sample(n=5, replace=True)\
                                    .sort_values(['TEXT2','bol_monad_num2'], 
                                                 ascending=True)
Hebrew_PrefixingBKLH4selection.head(10)

Hebrew_PrefixingBKLH4selection.to_excel('/Users/oliverglanz/Library/CloudStorage/OneDrive-AndrewsUniversity/1200_AUS-research/Fabric-TEXT/2_OTST551-2_Hebrew/BOL_exercises/BHSa4c_BOL_Hebrew_morphology_PrefixingBKLH4selection.xlsx', encoding='utf-16')