def strategy(ticket, df):
values = []
ema = df['EMA_9'][-1]
sma = df['SMA_40'][-1]
price = df['Último'][-1]
datum = Datum(ticket)
if datum in data:
datum = data[data.index(Datum(ticket))]
if ema > sma:
if datum.flag != 2:
notify(ticket, 2, df.index[-1])
save_datum(datum, 2)
elif ema < sma:
if datum.flag != 1:
notify(ticket, 1, df.index[-1])
save_datum(datum, 1)
elif datum.flag != 0:
save_datum(datum, 0)
else:
data.append(datum)
def strategy(ticket, df):
values = []
for window in windows:
values.append(df['SMA_' + str(window)][-1])
price = df['Último'][-1]
datum = Datum(ticket)
if datum in data:
datum = data[data.index(Datum(ticket))]
if price <= values[0] < values[1] < values[2] and bearish_fractal(df):
if datum.flag != 2:
notify(ticket, 2, df.index[-3])
save_datum(datum, 2)
elif price >= values[0] > values[1] > values[2] and bullish_fractal(
df):
if datum.flag != 1:
notify(ticket, 1, df.index[-3])
save_datum(datum, 1)
elif datum.flag != 0:
save_datum(datum, 0)
else:
data.append(datum)
def build_vdatum_input(self):
datum_frame = tk.Frame(self.controller_panel)
datum_frame.columnconfigure(0, weight=1)
datum_frame.grid(row=3, sticky=tk.EW)
tk.Label(datum_frame, text="VDatum Region",
font='Helvetica 10 bold').grid(row=0,
columnspan=1,
pady=(10, 0),
sticky=tk.EW)
datum = Datum()
regions, mcu_values, default_msg = datum.get_vdatum_region_mcus()
self.vdatum_regions = dict({(key, value)
for (key,
value) in zip(regions, mcu_values)})
self.vdatum_regions.update({default_msg: 0})
self.vdatum_region = tk.StringVar(self)
self.vdatum_region.set(default_msg)
self.vdatum_region_option_menu = tk.OptionMenu(
datum_frame,
self.vdatum_region,
*sorted(self.vdatum_regions.keys()),
command=self.update_vdatum_mcu_value)
self.vdatum_region_option_menu.config(width=self.control_panel_width,
anchor='w')
self.vdatum_region_option_menu.grid(sticky=tk.EW)
def setFeaturesTrain(self, data):
newData = []
words = []
for datum in data:
words.append(datum.word)
## This is so that the feature factory code doesn't
## accidentally use the true label info
previousLabel = "O"
followingLabel = "O"
for i in range(0, len(data)):
datum = data[i]
## MY EDIT
if i != len(data) - 1:
followingDatum = data[i + 1]
else:
followingDatum = datum
newDatum = Datum(datum.word, datum.label)
newDatum.followingLabel = followingDatum.label
newDatum.features = self.computeFeatures(words, previousLabel, i,
followingDatum.label)
newDatum.previousLabel = previousLabel
newData.append(newDatum)
previousLabel = datum.label
return newData
def setFeaturesTest(self, data):
newData = []
words = []
labels = []
labelIndex = {}
for datum in data:
words.append(datum.word)
if datum.label not in labelIndex:
labelIndex[datum.label] = len(labels)
labels.append(datum.label)
# This is so that the feature factory code doesn't
# accidentally use the true label info
for i in range(0, len(data)):
datum = data[i]
if i == 0:
previousLabel = "O"
datum.features = self.computeFeatures(words, previousLabel, i)
newDatum = Datum(datum.word, datum.label)
newDatum.features = self.computeFeatures(words, previousLabel, i)
newDatum.previousLabel = previousLabel
newData.append(newDatum)
else:
for previousLabel in labels:
datum.features = self.computeFeatures(words, previousLabel, i)
newDatum = Datum(datum.word, datum.label)
newDatum.features = self.computeFeatures(words, previousLabel, i)
newDatum.previousLabel = previousLabel
newData.append(newDatum)
return newData
def parse_csv_line(line, optimized_indexes=[]):
"""
Parse a csv line and return a list of string
"""
parsed_line = line.rstrip().split(SEPARATOR)
if len(optimized_indexes) == 0:
return Datum(parsed_line)
result = [
parsed_line[i] for i in range(len(parsed_line))
if i in optimized_indexes
]
return Datum(result)
def setFeaturesTrain(self, data):
newData = []
words = []
for datum in data:
words.append(datum.word)
## This is so that the feature factory code doesn't
## accidentally use the true label info
previousLabel = "O"
for i in range(0, len(data)):
datum = data[i]
newDatum = Datum(datum.word, datum.label)
newDatum.features = self.computeFeatures(words, previousLabel, i)
newDatum.previousLabel = previousLabel
newData.append(newDatum)
previousLabel = datum.label
return newData
def setFeaturesTest(self, data):
newData = []
words = []
labels = []
labelIndex = {}
for datum in data:
words.append(datum.word)
if not labelIndex.has_key(datum.label):
labelIndex[datum.label] = len(labels)
labels.append(datum.label)
## This is so that the feature factory code doesn't
## accidentally use the true label info
for i in range(0, len(data)):
datum = data[i]
if i == 0:
previousLabel = "O"
datum.features = self.computeFeatures(words, previousLabel, i)
newDatum = Datum(datum.word, datum.label)
newDatum.features = self.computeFeatures(words, previousLabel, i)
newDatum.previousLabel = previousLabel
newData.append(newDatum)
else:
for previousLabel in labels:
datum.features = self.computeFeatures(words, previousLabel, i)
newDatum = Datum(datum.word, datum.label)
newDatum.features = self.computeFeatures(words, previousLabel, i)
newDatum.previousLabel = previousLabel
newData.append(newDatum)
return newData
def standard_read(self):
with open(self.source_data_file) as fopen:
doc_id = 0
tokens, glabels = [], []
for line in fopen.readlines():
line = line.replace(' ', '\t')
if line.strip():
tokens.append(line.strip().split('\t')[0])
glabels.append(line.strip().split('\t')[1])
elif line.strip() == '' and tokens:
doc = ' '.join(tokens)
datum = Datum(doc_id, doc, tokens, glabels, [])
self.Datums.append(datum)
doc_id += 1
tokens, glabels = [], []
def readTestData(self, ch_aux):
data = []
for line in ch_aux.splitlines():
line_split = line.split()
# remove emtpy lines
if len(line_split) < 2:
continue
word = line_split[0]
label = line_split[1]
datum = Datum(word, label)
data.append(datum)
return data
def readData(self, filename):
data = []
for line in open(filename, 'r'):
line_split = line.split()
# remove emtpy lines
if len(line_split) < 2:
continue
word = line_split[0]
label = line_split[1]
datum = Datum(word, label)
data.append(datum)
return data
def strategy(ticket, mavs, time1):
datum = Datum(ticket)
b = check_mavs(ticket, mavs, time1)
if datum in data:
index = data.index(datum)
if data[index].flag is False and b == 1:
notify(ticket, 1, time1)
data[index].flag = True
elif data[index].flag is False and b == 2:
notify(ticket, 2, time1)
data[index].flag = True
elif b == 0:
data[index].flag = False
else:
data.append(datum)
def processLine(self, line):
line = line.strip()
line = line.lower()
line = line.replace('"', '')
line = line.replace(',', '')
line = line.replace('.', '')
line = line.replace('!', '')
line = line.replace("'", '')
line = line.replace(":", '')
line = line.replace(";", '')
if line == '':
return None
# p = PorterStemmer()
# print 'input line: \n' + line
# line = p.run_porter_stemmer(line)
# print 'output line: \n' + line
processed_tokens = Sentence()
processed_tokens.append(Datum("<s>")) # start symbol
tokens = line.split()
i = 0
while i < len(tokens):
token = tokens[i]
if token == '<err':
targ = tokens[i + 1]
targ_splits = targ.split('=')
# chop off the trailing '>'
correct_token = targ_splits[1][:-1]
correct_token_splits = correct_token.split()
if len(correct_token_splits) > 2: # targ with multiple words
# print 'targ with multiple words: "%s"' % targ
for correct_word in correct_token_splits:
processed_tokens.append(Datum(correct_word))
elif tokens[i + 3] != '</err>':
processed_tokens.append(Datum(correct_token))
else:
incorrect_token = tokens[i + 2]
processed_tokens.append(
Datum(correct_token, incorrect_token))
i += tokens[i:].index('</err>') + 1 # update index
else: # regular word
processed_tokens.append(Datum(token))
i += 1
processed_tokens.append(Datum("</s>"))
return processed_tokens
def processLine(self, line):
line = line.strip()
line = line.lower()
line = line.replace('"', '')
line = line.replace(',', '')
line = line.replace('.', '')
line = line.replace('!', '')
line = line.replace("'", '')
line = line.replace(":", '')
line = line.replace(";", '')
if line == '':
return None
processed_tokens = Sentence()
processed_tokens.append(Datum("<s>"))
tokens = line.split()
i = 0
while i < len(tokens):
token = tokens[i]
if token == '<err':
targ = tokens[i + 1]
targ_splits = targ.split('=')
correct_token = targ_splits[1][:-1]
correct_token_splits = correct_token.split()
if len(correct_token_splits) > 2:
for correct_word in correct_token_splits:
processed_tokens.append(Datum(correct_word))
elif tokens[i + 3] != '</err>':
processed_tokens.append(Datum(correct_token))
else:
incorrect_token = tokens[i + 2]
processed_tokens.append(
Datum(correct_token, incorrect_token))
i += tokens[i:].index('</err>') + 1
else: # regular word
processed_tokens.append(Datum(token))
i += 1
processed_tokens.append(Datum("</s>"))
return processed_tokens
def processLine(self, line):
'''
Reads line contains misspell words like the following
<ERR targ=That's> Thats </ERR> what <ERR targ=James> Jame </ERR>
Returns sentence including a list of Datum(correct word, incorrect word)
'''
processed_tokens = Sentence()
processed_tokens.append(Datum("<s>")) # start symbol
tokens = line.split()
i = 0
while i < len(tokens):
token = tokens[i]
# find out misspell word place
if token == "<err":
targ = tokens[i + 1]
targ_splits = targ.split("=")
correct_token = targ_splits[1][:
-1] # chop off the trailing '>'
correct_token_splits = correct_token.split()
if len(correct_token_splits) > 2: # targ with multiple words
print 'targ with multiple words: "%s"' % targ
for correct_word in correct_token_splits:
processed_tokens.append(Datum(correct_word))
# if miss one word in between, so no incorrect_token in this case
elif tokens[i + 3] != '</err>':
processed_tokens.append(Datum(correct_token))
else:
incorrect_token = tokens[i + 2]
processed_tokens.append(
Datum(correct_token, incorrect_token))
# move index to one after </ERR> symbol
i += tokens[i:].index('</err>') + 1
else:
# No mis-spell, correct sentence
processed_tokens.append(Datum(token))
i += 1
processed_tokens.append(Datum("</s>")) # stop symbol
return processed_tokens
>>> s.getErrorSentence()
['i', 'lov', 'girls']
- getCorrectSentence(): this method returns the right word. So;
>>> s.getCorrectSentence()
['i', 'love', 'girls']
- cleanSentence(): this method returns the right word but as a sentence. so;
>>> print s.cleanSentence()
i love girls
- isCorrection(): this method takes a list of strings and it iterates every word in the list and compare it with
the Datum instances in the 'data' variable. So;
>>> s.isCorrection(["i", "love", "girls"])
True
>>> s.isCorrection(["i", "lov", "girls"])
False
>>> s.isCorrection(["i", "lov", "Girls"])
False
- getErrorIndex(): this method returns the index of the wrong word in the sentence and returns -1 if
there is no error. So;
>>> s.getErrorIndex()
1
"""
if __name__ == "__main__":
lst = [Datum("i"), Datum("love", "lov"), Datum("girls")]
s = Sentence(lst)
s.put(0, Datum('I'))
print s.isCorrection(["I", "love", "girls"])
