def check_spam(sender, data, pred =[]):
with window("Simple SMS Spam Filter"):
if pred == []:
#runs only once - the the button is first clicked
#and pred[-1] widget doesn't exist
add_spacing(count=12)
add_separator()
add_spacing(count=12)
#collect input, pre-process and get prediction
input_value = get_value("Input")
input_value = pre_process(input_value)
pred_text, text_colour = predict(input_value)
#store prediction inside the pred list
pred.append(pred_text)
#display prediction to user
add_text(pred[-1], color=text_colour)
else:
#hide prediction widget
hide_item(pred[-1])
#collect the current user input and evaluate it
input_value = get_value("Input")
input_value = pre_process(input_value)
pred_text, text_colour = predict(input_value)
#store prediction inside the pred list
pred.append(pred_text)
add_text(pred[-1], color=text_colour)
def check_spam(sender, data, pred=[]):
with window("Simple SMS Spam Filter"):
if pred == []:
add_spacing(count=12)
add_separator
add_spacing(count=12)
input_value = get_value("Input")
input_value = pre_process(input_value)
pred_text, text_colour = predict(input_value)
pred.append(pred_text)
add_text(pred[-1], color=text_colour)
else:
hide_item(pred[-1])
input_value = get_value("Input")
input_value = pre_process(input_value)
pred_text, text_colour = predict(input_value)
pred.append(pred_text)
add_text(pred[-1], color=text_colour)
def calc_thiessen():
print("*************************************************************")
print("* Cálculo da precipitação média usando o método de Thiessen *")
print("*************************************************************")
hidroweb_dir = check_dir(
input("Informe o diretório com os dados das estações do Hidroweb:\n"),
'dir')
inventory = check_dir(
input("Caminho completo para o inventário das estações:\n"),
'file',
ext='.csv')
shp = check_dir(input("Shapefile com o traçado da bacia hidrográfica:\n"),
'file',
ext='.shp')
poly = input("Nome do polígono da bacia hidrodráfica:\n")
attr = input("Nome do atributo para seleção do polígono:\n")
buffer = input("Valor do buffer:\n")
date = check_date()
dir_out = check_out(input("Informe o diretório de saída:\n"))
loc_stations = pre_process(hidroweb_dir, inventory)
if not attr:
attr = 'basiname' # nome padrão do atributo caso não informado
if buffer:
buffer = float(buffer)
else:
buffer = False # padrão caso não informado
# extrai vertices do poligono (poly) do shape informado
vertices = getvert(shp, poly, attr=attr, buffer=buffer)
# verifica quais postos estão dentro do polígono
isin = isinpoly3(loc_stations[:, 2], loc_stations[:, 1], vertices)
# seleciona apenas postos dentro do polígono
estations_in = loc_stations[isin, :]
# converte date de string para datetime
date = pd.to_datetime(date, format='%d/%m/%Y')
# extrai precipitação dos postos dentro do polígono para a data informada
pr_estations = open_files(estations_in, hidroweb_dir, date)
# cálculo da precipitação média usando o método de thiessen
pr_med = thiessen(pr_estations[:, 1], pr_estations[:, 0], vertices[:, 0],
vertices[:, 1], pr_estations[:, 2])
# salva a precipitação média no formato .csv
save_csv(dir_out, pr_med, date, poly)
return None
#imports
import pandas as pd
import numpy as np
import seaborn as sns
import matplotlib.pyplot as plt
import functions as func #file containing the user created functions
#read csv files and create dataframes
train = pd.read_csv('train.csv')
test = pd.read_csv('test.csv')
#main
#.apply allows to apply functions to each row or column
df = func.pre_process(train)
df.to_csv('dataframe.csv')
features_select_K = func.feature_selection(
df.drop(['AnimalID'], axis=1), 'OutcomeType', 'KBest', 10
) #need to concat with class to obtain final dataframe for classification
#features_select_Fdr = func.feature_selection(df.drop(['AnimalID'],axis=1),'OutcomeType','Fdr') #need to concat with class to obtain final dataframe for classification
#features_select_Fwe = func.feature_selection(df.drop(['AnimalID'],axis=1),'OutcomeType','Fwe') #need to concat with class to obtain final dataframe for classification
#features_select_Pct = func.feature_selection(df.drop(['AnimalID'],axis=1),'OutcomeType','Pct') #need to concat with class to obtain final dataframe for classification
print('KBest:', features_select_K)
#print('Fdr:',features_select_Fdr)
#print('Fwe:',features_select_Fwe)
#print('Fwe:',features_select_Pct)
#print('KBest:',features_select_K.columns)
#print('Pct:',features_select_Pct.columns)
import sys
reload(sys)
sys.setdefaultencoding('utf8')
from path import add_parent_to_path
add_parent_to_path()
from functions import read_corpus, replace_compounds, reddy_ncs, pre_process, print_every, read_ncs, \
write_to_file, get_preprocess_args
import logging
from config import logging_config
import nltk
nltk.download('punkt')
nltk.download('wordnet')
if __name__ == '__main__':
logging.info('Reading train and evaluation ncs')
args = get_preprocess_args()
r_ncs, _ = reddy_ncs(args.p2ec)
ncs = read_ncs(args.p2tc)
ncs.extend(r_ncs)
logging.info('Reading corpus')
sentences = read_corpus(args.p2corp)
lemmatizer = nltk.stem.WordNetLemmatizer()
output = []
logging.info('Replacing ncs in corpus')
for i in range(0, len(sentences)):
s = sentences[i]
print_every(s, i + 1, 10000)
output.append(replace_compounds(pre_process(s, lemmatizer), ncs))
logging.info('Writing results in ' + args.p2out)
write_to_file(output, args.p2out)
