Modified prints + sqlalchemy and psycopg2cffi made optional

This commit is contained in:
Luka 2021-04-15 14:16:34 +02:00
parent 39692e839f
commit d67976c3d9
8 changed files with 26 additions and 20 deletions

View File

@ -2,6 +2,7 @@ import argparse
import os
import sys
import tqdm
import logging
good_lemmas = ["absurd", "absurdnost", "akuten", "akutno", "alkohol", "alkoholen", "aluminijast", "ananas", "aplikacija", "aplikativen", "aranžma", "arbiter", "armada", "avtomatičen", "avtomatiziran", "babica", "bajen", "bajka", "bakren", "bambusov", "barvan", "barvanje", "baseballski", "bazar", "bazičen", "belina", "bezgov", "bičati", "bife", "bilka", "biomasa", "biotop", "birma", "bivol", "blago", "blaženost", "bliskavica", "bobnič", "bolha", "bolnišnica", "bor", "borov", "borovničev", "brati", "briljant", "briti", "brusiti", "bučanje", "cikličen", "civilizacija", "dopust", "drama", "drezati", "duda", "dvorezen", "embalaža", "faks", "farsa", "glasno", "informiranje", "interier", "intima", "intimno", "investirati", "ironično", "istovetiti", "izvožen", "jagoda", "jeklar", "jezik", "karbon", "kitara", "kodrast", "molče", "mučiti", "novinarski", "obala", "občevati", "okrasiti", "pajčevina", "panoga", "prevajanje", "prevajati", "previti", "prihraniti", "priloga", "prisluškovati", "sopara"]
@ -15,14 +16,14 @@ def main(args):
for fidx, filename in enumerate(filepaths):
with open(filename, 'r') as fp:
print("loading next...", end="", flush=True)
logging.info("loading next...")
line = fp.readline()
lemma_rows = [idx for idx, cell in enumerate(line.split(",")) if "_Lemma" in cell]
file_lines = fp.read().split("\n")
for lidx, good_lemma in enumerate(good_lemmas):
spaces = " " * 20 if lidx == 0 else ""
print("\r{}.{} / {}.{}{}".format(fidx, lidx, N2, N1, spaces), end="", flush=True)
logging.info("\r{}.{} / {}.{}{}".format(fidx, lidx, N2, N1, spaces))
for line in file_lines:
if good_lemma not in line:

View File

@ -1,5 +1,6 @@
from math import log2
import re
import logging
from luscenje_struktur.component import ComponentType
@ -165,9 +166,9 @@ class StatsFormatter(Formatter):
new_key = (sidx, idx, '')
if new_key in self.colocation_ids.dispersions:
key = new_key
print('Dispersions fixed.')
logging.info('Dispersions fixed.')
else:
print('Dispersions not fixed.')
logging.info('Dispersions not fixed.')
if key in self.colocation_ids.dispersions:
distribution = self.colocation_ids.dispersions[key]
else:

View File

@ -29,13 +29,13 @@ def load_files(args, database, w_collection=None, input_corpus=None):
database.init("CREATE TABLE Files ( filename varchar(2048) )")
for idx, fname in enumerate(filenames):
print("FILE ", fname, "{}/{}".format(idx, len(filenames)))
logging.info("FILE " + fname + "{}/{}".format(idx, len(filenames)))
extension = pathlib.Path(fname).suffix
# check if file with the same name already loaded...
loaded = database.execute("SELECT * FROM Files WHERE filename=?", (fname,)).fetchone()
if loaded is not None:
print("ALREADY LOADED")
logging.info("ALREADY LOADED")
continue
if extension == ".xml":

View File

@ -2,6 +2,7 @@ import gc
from collections import defaultdict
from ast import literal_eval
from time import time
import logging
from luscenje_struktur.match import StructureMatch
from luscenje_struktur.representation_assigner import RepresentationAssigner
@ -104,7 +105,7 @@ class MatchStore:
def set_representations(self, word_renderer, structures, sloleks_db=None):
step_name = 'representation'
if self.db.is_step_done(step_name):
print("Representation step already done, skipping")
logging.info("Representation step already done, skipping")
return
num_inserts = 1000
@ -148,7 +149,7 @@ class MatchStore:
dispersions[(str(structure_id), component_id, lemma)] += 1
self.dispersions = dict(dispersions)
print("Storing dispersions...")
logging.info("Storing dispersions...")
self.store_dispersions()
self.db.step_is_done(step_name)

View File

@ -1,4 +1,5 @@
import time
import logging
try:
from tqdm import tqdm
@ -21,10 +22,10 @@ class Progress:
for n, el in enumerate(iterable):
now = time.time()
if now - last_report > REPORT_ON:
print("\r{}: {}/{}".format(description, n, total), end="")
logging.info("\r{}: {}/{}".format(description, n, total), end="")
last_report = now
yield el
print(" -> {}".format(time.time() - start_time))
logging.info(" -> {}".format(time.time() - start_time))
else:
yield from tqdm(iterable, desc=description, total=total)

View File

@ -1,17 +1,17 @@
import gc
from psycopg2cffi import compat
compat.register()
from sqlalchemy.ext.declarative import declarative_base
from sqlalchemy.orm import Session, aliased
from sqlalchemy import create_engine
from luscenje_struktur.codes_tagset import TAGSET, CODES, CODES_TRANSLATION, POSSIBLE_WORD_FORM_FEATURE_VALUES
class SloleksDatabase:
def __init__(self, db, load_sloleks):
from psycopg2cffi import compat
compat.register()
from sqlalchemy.ext.declarative import declarative_base
from sqlalchemy.orm import Session
from sqlalchemy import create_engine
global Lexeme, LexemeFeature, SyntacticStructure, StructureComponent, Feature, LexicalUnitLexeme, LexicalUnit, LexicalUnitType, Category, Sense, Measure, LexicalUnitMeasure, Corpus, Definition, WordForm, WordFormFeature, FormRepresentation
[db_user, db_password, db_database, db_host] = db.split(':')
@ -153,6 +153,7 @@ class SloleksDatabase:
def get_word_form(self, lemma, msd, data, align_msd=False):
# modify msd as required
from sqlalchemy.orm import aliased
msd = list(msd)
if 'msd' in data:
for key, value in data['msd'].items():

View File

@ -1,4 +1,5 @@
from datetime import timedelta, datetime
import logging
class TimeInfo:
def __init__(self, to_go):
@ -14,5 +15,5 @@ class TimeInfo:
seconds = sum(self.times) / len(self.times)
td = timedelta(seconds = int(seconds * self.to_go))
ft = datetime.now() + td
print("Going to finish in {}".format(ft.strftime("%d/%m @ %H:%M")))
logging.info("Going to finish in {}".format(ft.strftime("%d/%m @ %H:%M")))

View File

@ -1,7 +1,7 @@
from collections import defaultdict, Counter
from luscenje_struktur.progress_bar import progress
import logging
class WordStats:
def __init__(self, lemma_features, db):
@ -46,7 +46,7 @@ class WordStats:
def generate_renders(self):
step_name = 'generate_renders'
if self.db.is_step_done(step_name):
print("Skipping GenerateRenders, already complete")
logging.info("Skipping GenerateRenders, already complete")
return
lemmas = [lemma for (lemma, ) in self.db.execute("SELECT DISTINCT lemma FROM UniqWords")]