added cols support for get database

README

@@ -11,17 +11,35 @@ pip install grcriddles
 Use from Python/IPython console:
 
 ```python
-  # import database getter
-  from grcriddles import get_database
-  a = get_database()
-  # filter words
-  a = a[a[0].str.contains("ΑΜΦΕΚΑΛΥ")]
-  # sort and print word info
-  words = a.sort_values(0)
-  words = words[[0, 1, 3, 4, 5, 7, 8]]
-  words.columns = ['Word', 'Count', 'Chars', 'Isopsephy', 'Syllables', 'Vowels', 'Mutes']
-  words.set_index('Word', inplace=True)
-  words
+  # get words with length 9, isopsephy 1697, consonants 5,
+  # and the first three syllables having 2 letters each
+  # syllable count is going to be 4 with above parameters
+  words = get_database({0: 'Word', 1: 'Count', 3: 'Chars', 4: 'Isopsephy', 5: 'Syllables', 7: 'Vowels', 8: 'Mutes'})
+  a = words[words['Isopsephy'] == 1697]
+  a = a[a['Chars'] == 9]
+  a = a[a['Mutes'] == 5]
+  a = a[a.apply(lambda x: len(x['Syllables'][0]) == 2 and \
+                          len(x['Syllables'][1]) == 2 and \
+                          len(x['Syllables'][2]) == 2, axis=1)]
+  # output words ordered alphabetically
+  a.sort_index()
+```
+
+Output:
+
+```txt
+             Count    Chars  Isopsephy          Syllables  Vowels       Mutes
+  Word
+  ΑΜΦΕΚΑΛΥΨ      1        9       1697  [ΑΜ, ΦΕ, ΚΑ, ΛΥΨ]       4           5
+  ΛΗΛΥΘΟΤΩΝ      1        9       1697  [ΛΗ, ΛΥ, ΘΟ, ΤΩΝ]       4           5
+  ΜΕΤΑΝΑΣΤΩ      1        9       1697  [ΜΕ, ΤΑ, ΝΑ, ΣΤΩ]       4           5
+  ΣΥΝΩΚΙΣΘΗ     13        9       1697  [ΣΥ, ΝΩ, ΚΙ, ΣΘΗ]       4           5
+```
+
+```python
+  # get words containing ΑΜΦΕΚΑΛΥ stem word
+  b = words.filter(like="ΑΜΦΕΚΑΛΥ", axis=0)
+  b.sort_index()
 ```
 
 Output:
@@ -38,7 +56,7 @@ Word
 ΑΜΦΕΚΑΛΥΨΕΝ      20     11       1752   [ΑΜ, ΦΕ, ΚΑ, ΛΥ, ΨΕΝ]       5      6
 ```
 
-Docs:
+### Docs
 
 Developer documentation: http://grcriddles.readthedocs.io/en/latest/
 

README.md

@@ -11,17 +11,35 @@ pip install grcriddles
 Use from Python/IPython console:
 
 ```python
-  # import database getter
-  from grcriddles import get_database
-  a = get_database()
-  # filter words
-  a = a[a[0].str.contains("ΑΜΦΕΚΑΛΥ")]
-  # sort and print word info
-  words = a.sort_values(0)
-  words = words[[0, 1, 3, 4, 5, 7, 8]]
-  words.columns = ['Word', 'Count', 'Chars', 'Isopsephy', 'Syllables', 'Vowels', 'Mutes']
-  words.set_index('Word', inplace=True)
-  words
+  # get words with length 9, isopsephy 1697, consonants 5,
+  # and the first three syllables having 2 letters each
+  # syllable count is going to be 4 with above parameters
+  words = get_database({0: 'Word', 1: 'Count', 3: 'Chars', 4: 'Isopsephy', 5: 'Syllables', 7: 'Vowels', 8: 'Mutes'})
+  a = words[words['Isopsephy'] == 1697]
+  a = a[a['Chars'] == 9]
+  a = a[a['Mutes'] == 5]
+  a = a[a.apply(lambda x: len(x['Syllables'][0]) == 2 and \
+                          len(x['Syllables'][1]) == 2 and \
+                          len(x['Syllables'][2]) == 2, axis=1)]
+  # output words ordered alphabetically
+  a.sort_index()
+```
+
+Output:
+
+```txt
+             Count    Chars  Isopsephy          Syllables  Vowels       Mutes
+  Word
+  ΑΜΦΕΚΑΛΥΨ      1        9       1697  [ΑΜ, ΦΕ, ΚΑ, ΛΥΨ]       4           5
+  ΛΗΛΥΘΟΤΩΝ      1        9       1697  [ΛΗ, ΛΥ, ΘΟ, ΤΩΝ]       4           5
+  ΜΕΤΑΝΑΣΤΩ      1        9       1697  [ΜΕ, ΤΑ, ΝΑ, ΣΤΩ]       4           5
+  ΣΥΝΩΚΙΣΘΗ     13        9       1697  [ΣΥ, ΝΩ, ΚΙ, ΣΘΗ]       4           5
+```
+
+```python
+  # get words containing ΑΜΦΕΚΑΛΥ stem word
+  b = words.filter(like="ΑΜΦΕΚΑΛΥ", axis=0)
+  b.sort_index()
 ```
 
 Output:
@@ -38,7 +56,7 @@ Word
 ΑΜΦΕΚΑΛΥΨΕΝ      20     11       1752   [ΑΜ, ΦΕ, ΚΑ, ΛΥ, ΨΕΝ]       5      6
 ```
 
-Docs:
+### Docs
 
 Developer documentation: http://grcriddles.readthedocs.io/en/latest/
 

doc/appendix2.rst

@@ -5,29 +5,49 @@ Minimum code to solve isopsephical riddles in the Pseudo-Sibylline oracles. This
 requires `functions.py` script and `greek_words_corpora.csv` file reside in the
 same directory.
 
-.. code-block:: python
+.. code-block:: bash
 
-  from functions import get_database
+  pip install grcriddles
 
-  # get words with length 9, isopsephy 1697, syllable count 4, consonants 5,
-  # and the first three syllables having 2 letters each
-  a = get_database()
-  a = a[a[4] == 1697]
-  a = a[a[3] == 9]
-  a = a[a[6] == 4]
-  a = a[a[8] == 5]
-  a = a[a.apply(lambda x: len(x[5][0]) == 2 and len(x[5][1]) == 2 and len(x[5][2]) == 2, axis=1)]
+.. code-block:: python
 
+  from grcriddles import get_database
+  # get words with length 9, isopsephy 1697, consonants 5,
+  # and the first three syllables having 2 letters each
+  # syllable count is going to be 4 with above parameters
+  words = get_database({0: 'Word', 1: 'Count', 3: 'Chars', 4: 'Isopsephy', 5: 'Syllables', 7: 'Vowels', 8: 'Mutes'})
+  a = words[words['Isopsephy'] == 1697]
+  a = a[a['Chars'] == 9]
+  a = a[a['Mutes'] == 5]
+  a = a[a.apply(lambda x: len(x['Syllables'][0]) == 2 and \
+                          len(x['Syllables'][1]) == 2 and \
+                          len(x['Syllables'][2]) == 2, axis=1)]
   # output words ordered alphabetically
-  words = a.sort_values(0)
-  words = words[[0, 1, 3, 4, 5, 7, 8]]
-  words.columns = ['Word', 'Count', 'Letters', 'Isopsephy', 'Syllables', 'Vowels', 'Consonants']
-  words.set_index('Word', inplace=True)
-  words
-
-  # search exact match(es) for the word
-  from functions import search_words_from_corpora, perseus_dir, first1k_dir
-  search_words_from_corpora(["ΑΜΦΕΚΑΛΥΨ"], [perseus_dir, first1k_dir], None, True)
-
-  # search partial match(es) for the word
-  search_words_from_corpora(["ΑΜΦΕΚΑΛΥΨ"], [perseus_dir, first1k_dir], None, False)
+  a.sort_index()
+
+.. code-block:: text
+
+             Count    Chars  Isopsephy          Syllables  Vowels       Mutes
+  Word
+  ΑΜΦΕΚΑΛΥΨ      1        9       1697  [ΑΜ, ΦΕ, ΚΑ, ΛΥΨ]       4           5
+  ΛΗΛΥΘΟΤΩΝ      1        9       1697  [ΛΗ, ΛΥ, ΘΟ, ΤΩΝ]       4           5
+  ΜΕΤΑΝΑΣΤΩ      1        9       1697  [ΜΕ, ΤΑ, ΝΑ, ΣΤΩ]       4           5
+  ΣΥΝΩΚΙΣΘΗ     13        9       1697  [ΣΥ, ΝΩ, ΚΙ, ΣΘΗ]       4           5
+
+.. code-block:: python
+
+  # get words containing ΑΜΦΕΚΑΛΥ stem word
+  b = words.filter(like="ΑΜΦΕΚΑΛΥ", axis=0)
+  b.sort_index()
+
+.. code-block:: text
+
+                Count  Chars  Isopsephy               Syllables  Vowels  Mutes
+  Word
+  ΑΜΦΕΚΑΛΥΠΤΕ       3     11       1382   [ΑΜ, ΦΕ, ΚΑ, ΛΥ, ΠΤΕ]       5      6
+  ΑΜΦΕΚΑΛΥΠΤΟΝ      2     12       1497  [ΑΜ, ΦΕ, ΚΑ, ΛΥ, ΠΤΟΝ]       5      7
+  ΑΜΦΕΚΑΛΥΦΘΗ       2     11       1514   [ΑΜ, ΦΕ, ΚΑ, ΛΥ, ΦΘΗ]       5      6
+  ΑΜΦΕΚΑΛΥΨ         1      9       1697       [ΑΜ, ΦΕ, ΚΑ, ΛΥΨ]       4      5
+  ΑΜΦΕΚΑΛΥΨΑΝ       2     11       1748   [ΑΜ, ΦΕ, ΚΑ, ΛΥ, ΨΑΝ]       5      6
+  ΑΜΦΕΚΑΛΥΨΕ       18     10       1702    [ΑΜ, ΦΕ, ΚΑ, ΛΥ, ΨΕ]       5      5
+  ΑΜΦΕΚΑΛΥΨΕΝ      20     11       1752   [ΑΜ, ΦΕ, ΚΑ, ΛΥ, ΨΕΝ]       5      6

doc/appendix3.rst

@@ -0,0 +1,11 @@
+Appendix 3 - Search results
+===========================
+
+.. code-block:: python
+
+  # search exact match(es) for the word from both perseus and first1k corpora
+  from functions import search_words_from_corpora, perseus_dir, first1k_dir
+  search_words_from_corpora(["ΑΜΦΕΚΑΛΥΨ"], [perseus_dir, first1k_dir], None, True)
+
+  # search partial match(es) for the word from both perseus and first1k corpora
+  search_words_from_corpora(["ΑΜΦΕΚΑΛΥΨ"], [perseus_dir, first1k_dir], None, False)

grcriddles/__init__.py

@@ -2,7 +2,7 @@
 # -*- coding: utf-8 -*-
 # file: __init__.py
 
-__version__ = "0.1.4"
+__version__ = "0.1.6"
 
 from .functions import Abnum, greek, syllabify, Counter, HTML, display_html, \
                        display_side_by_side, remove, download_with_indicator, \

grcriddles/functions.py

@@ -295,7 +295,7 @@ def get_stats(fl):
     return ccontent, chars, lwords
 
 # get word database
-def get_database():
+def get_database(cols = None):
     global database
     if not database:
         # try to read from the current directory
@@ -313,7 +313,16 @@ def get_database():
         df[7] = df[7].apply(lambda x: int(x))
         df[8] = df[8].apply(lambda x: int(x))
         database = df
-    return database.copy()
+    # rename columns and set index
+    if cols:
+        words = database.copy()
+        words = words[list(cols.keys())]
+        words.columns = list(cols.values())
+        if 0 in cols:
+            words.set_index(cols[0], inplace=True)
+        return words
+    else:
+        return database.copy()
 
 # display tables side by side, jupyter notebook helper
 def display_side_by_side(**kwargs):

setup.py

@@ -6,7 +6,7 @@
 
 #python setup.py sdist upload
 
-version = 'v0.1.5'
+version = 'v0.1.6'
 
 name = 'grcriddles'