def main():
cluster_rows = dict()
for i in range(10):
filereader = FileReader(f"./full_tweets/cluster_{i}.csv")
cluster_rows[i] = filereader.get_rows()
with codecs.open("cluster_rows.csv", "w+") as o:
o.write("Cluster Number" + "," + "User Name" + "," + "user_id\t" + "," + "No of Tweets\t\t" + "," + "Tweet_id\t" + ","
"Retweet Count\t" + "," + "Inf Score\t" + "," + "Tweet\n")
for key, value in cluster_rows.items():
lines = ""
for v in value:
line = str(key)
line += ","
line += ",".join(v)
line += "\n"
lines += line
o.write(lines)
def get_starter_template():
# Init
filereader = FileReader()
weaponsdict = []
weapons_read = []
weapons = []
information_number = 4 * 2
# Scan Dir for Weapon Files
files = [f for f in os.listdir("./") if isfile(join("./", f))]
files.remove("WeaponTemplates.py")
# Append File Content
for i in range(len(files)):
weapons_read.append(
filereader.line(os.path.dirname(__file__) + "/" + files[i]))
# Write Data to List
for i in weapons_read:
for _i in i:
item = _i.split("=")
for _item in item:
_item = _item.strip(' ')
if "??" in item:
_item.replace("??", "100")
weapons.append(_item)
# Convert List to Dict
weapon = []
for item in weapons:
weapon.append(item)
if len(weapon) % information_number == 0:
weaponsdict.append(Functions.list_to_dict(weapon))
del weapon
# Return Result
return weaponsdict
def main():
os.chdir("../step_9")
reader = FileReader("step_9_output_inf_user_tweets.csv")
user_n_tweets = reader.rows
dict_of_users = RowSeperater(user_n_tweets).seperate_rows()
tweet_dump = []
dict_of_id_words = {}
for key, value in dict_of_users.items():
for k, v in value.items():
words_list = TweetNormalizer(v).words
words_list = StopWordsRemover(words_list).reduced_words
stemmed_words = WordStemmer(words_list).implement_stemming()
lem_words = WordLemmatizer(stemmed_words).implement_lemmatizing()
lem_words = list(set(lem_words))
dict_of_id_words[k] = lem_words
tweet_dump += lem_words
tweet_dump = list(set(tweet_dump))
# print(len(tweet_dump))
pprint(dict_of_id_words)
from Day2.InventorySystem import InventorySystem
from utils.FileReader import FileReader
list_of_ids = FileReader.read('../sources/day2.txt')
system = InventorySystem(list_of_ids)
print('Checksum : ', system.checksum())
print('Common letters : ', system.find_boxes_common_letters())
from Day1.Chronal_Calibration import Device
from utils.FileReader import FileReader
sequence = FileReader.read('../sources/day1.txt')
device = Device()
device.calibrate(sequence)
print('Final frequency state :', device.final_frequency)
print('Frequency that occured twice :', device.frequency)
def test_read_should_return_array_of_lines(self, mock):
lines = FileReader.read('./path/to/file.txt')
assert lines == ['line1', 'line2']
from Day3.Claim import Claim
from Day3.Diplomat import Diplomat
from utils.FileReader import FileReader
list_of_claims_scheme = FileReader.read('../sources/day3.txt')
list_of_claims = [Claim.parse(claim) for claim in list_of_claims_scheme]
diplomate = Diplomat(list_of_claims)
print(diplomate.number_of_conflicts())
def create_training_data(self):
# reading Porosity
porosityMatrices = FileReader.read("data/" + self.attributes_files[0],
20)
self.x_size, self.y_size = porosityMatrices[0].shape
x = porosityMatrices[0].flatten()
y = porosityMatrices[1].flatten()
porosity = porosityMatrices[2].flatten()
col = porosityMatrices[3].flatten()
row = porosityMatrices[4].flatten()
# reading Porosity-effective
porosityEffectiveMatrix = FileReader.read(
"data/" + self.attributes_files[1], 20)
porosity_effective = porosityEffectiveMatrix[2].flatten()
# reading ntglinear_model,
ntgMatrix = FileReader.read("data/" + self.attributes_files[2], 20)
ntg = ntgMatrix[2].flatten()
# reading sw_base
swBaseMatrix = FileReader.read("data/" + self.attributes_files[3], 20)
sw_base = swBaseMatrix[2].flatten()
# reading sg_base
sgBaseMatrix = FileReader.read("data/" + self.attributes_files[4], 20)
sg_base = sgBaseMatrix[2].flatten()
# reading dsg
dsgMatrix = FileReader.read("data/" + self.attributes_files[5], 20)
dsg = dsgMatrix[2].flatten()
# reading dsw
dswMatrix = FileReader.read("data/" + self.attributes_files[6], 20)
dsw = dswMatrix[2].flatten()
# reading actual dRMS
fair_int_dRMSMatrix_10m = FileReader.read(
"data/" + self.attributes_files[7], 20)
xdRMS = fair_int_dRMSMatrix_10m[0].flatten()
ydRMS = fair_int_dRMSMatrix_10m[1].flatten()
fair_int_dRMS_10m = fair_int_dRMSMatrix_10m[2].flatten()
# reading actual dRMS
fair_int_dRMSMatrix_20m = FileReader.read(
"data/" + self.attributes_files[8], 20)
xdRMS = fair_int_dRMSMatrix_20m[0].flatten()
ydRMS = fair_int_dRMSMatrix_20m[1].flatten()
fair_int_dRMS_20m = fair_int_dRMSMatrix_20m[2].flatten()
# reading synthetic dRMS
fair_int_dRMSMatrix = FileReader.read(
"data/" + self.attributes_files[9], 20)
xdRMS = fair_int_dRMSMatrix[0].flatten()
ydRMS = fair_int_dRMSMatrix[1].flatten()
fair_int_dRMS = fair_int_dRMSMatrix[2].flatten()
for i in range(len(x)):
if math.isnan(x[i]) or math.isnan(y[i]) or math.isnan(
dsg[i]) or math.isnan(dsw[i]) or math.isnan(
xdRMS[i]) or math.isnan(ydRMS[i]) or math.isnan(
fair_int_dRMS_10m[i]) or math.isnan(
fair_int_dRMS_20m[i]) or math.isnan(
fair_int_dRMS[i]):
#nothing
print("")
else:
self.x.append(x[i])
self.y.append(y[i])
self.porosity.append(porosity[i])
self.porosity_effective.append(porosity_effective[i])
self.col.append(col[i])
self.row.append(row[i])
self.ntg.append(ntg[i])
self.sw_base.append(sw_base[i])
self.sg_base.append(sg_base[i])
self.dsg.append(dsg[i])
self.dsw.append(dsw[i])
self.xdRMS.append(xdRMS[i])
self.ydRMS.append(ydRMS[i])
self.fair_int_dRMS_10m.append(fair_int_dRMS_10m[i])
self.fair_int_dRMS_20m.append(fair_int_dRMS_20m[i])
self.fair_int_dRMS.append(fair_int_dRMS[i])