def _get_value(self):
"""Parse values based on "m$n", ";" and ")" delimiters"""
RV = []
# first value, between "m$n" and ";"
# add +4 because "m$n" delimiter has 3 chars, plus 1 white space
value_start = self.row[0].find("m$n") + 4
value_end = self.row[0].find(";")
# get substring, convert to float and append
str_value = self.row[0][value_start:value_end]
float_value = convert_to_float(str_value)
RV.append(float_value)
# second value, between last "m$n" and ")"
# add +4 because "m$n" delimiter has 3 chars, plus 1 white space
value_start = self.row[0].rfind("m$n") + 4
value_end = self.row[0].find(")")
# get substring, convert to float and append
str_value = self.row[0][value_start:value_end]
float_value = convert_to_float(str_value)
RV.append(float_value)
return RV
def get_rights_issue(ticker, start_date, end_date):
'''
获取股票已实施配股数据。
Parameters
----------
ticker
'600340'
start_date
'20100101'
end_date
'20150101'
Returns
--------
DataFrame
index ex_rights_date
columns
'ex_rights_date','rights_issue_per_stock','rights_issue_price',
'transfer_rights_issue_per_stock','transfer_price'
(除权日,每股配股,配股价，每股转配，每股转配价)
'''
sql_select = '''
SELECT [除权日]
,[配股比例分子]
,[配股价格]
,[转配比例分子]
,[转让费]
FROM [BasicData].[dbo].[Yi_RightsIssue]
WHERE [除权日] is not null
AND [stockcode] = '%s'
''' % (ticker)
cur.execute(sql_select)
data = cur.fetchall()
columns = [
'ex_rights_date', 'rights_issue_numerator', 'rights_issue_price',
'transfer_rights_issue_numerator', 'transfer_rights_issue_fee'
]
df = pd.DataFrame(data, columns=columns)
df = df.fillna(0)
df['ex_rights_date'] = matlab_time_convert(df['ex_rights_date'])
df['rights_issue_price'] = convert_to_float(df['rights_issue_price'])
df['rights_issue_per_stock'] = \
convert_to_float(df['rights_issue_numerator']) / 10.0
df['transfer_rights_issue_per_stock'] = \
convert_to_float(df['transfer_rights_issue_numerator']) / 10.0
df['transfer_price'] = \
df['rights_issue_price'] + convert_to_float(df['transfer_rights_issue_fee'])
df = df[[
'ex_rights_date', 'rights_issue_per_stock', 'rights_issue_price',
'transfer_rights_issue_per_stock', 'transfer_price'
]]
df = df.set_index('ex_rights_date', drop=False)
df = df.sort_index()
df = df[start_date:end_date]
return df
def update_rover(Rover, data):
# Retrieve current kinematic and control values
Rover.vel = convert_to_float(data["speed"]) # meters/sec
Rover.pos = [
convert_to_float(pos.strip()) for pos in data["position"].split(';')
]
Rover.yaw = convert_to_float(data["yaw"])
Rover.pitch = convert_to_float(data["pitch"])
Rover.roll = convert_to_float(data["roll"])
Rover.throttle = convert_to_float(data["throttle"])
Rover.steer = convert_to_float(data["steering_angle"])
# Initialize start time and sample positions
if Rover.start_time == None:
Rover.start_time = time.time()
Rover.total_time = 0
samples_xpos = np.int_([
convert_to_float(pos.strip())
for pos in data["samples_x"].split(';')
])
samples_ypos = np.int_([
convert_to_float(pos.strip())
for pos in data["samples_y"].split(';')
])
Rover.samples_pos = (samples_xpos, samples_ypos)
Rover.samples_to_find = np.int(data['sample_count'])
Rover.homePos = (Rover.pos[0], Rover.pos[1])
Log("Home=" + str(Rover.homePos))
else:
tot_time = time.time() - Rover.start_time
if np.isfinite(tot_time):
Rover.total_time = tot_time
# Near sample flag
Rover.near_sample = np.int(data["near_sample"])
# Picking up flag
Rover.picking_up = np.int(data["picking_up"])
# Update number of rocks collected
Rover.samples_collected = Rover.samples_to_find - np.int(
data["sample_count"])
# Get the current image from the center camera of the rover
imgString = data["image"]
image = Image.open(BytesIO(base64.b64decode(imgString)))
Rover.img = np.asarray(image)
# Create dict conta8iner for various processed images
Rover.procImage = {}
Rover.procImage['POVRaw'] = Rover.img
#LogRoverState(Rover, data)
# Return updated Rover and separate image for optional saving
return Rover, image
def get_dividend(ticker, start_date, end_date):
'''
获取股票时间段内实施的分红送股转增数据。
Parameters
----------
ticker
'600340'
start_date
'20100101'
end_date
'20150101'
Returns
--------
DataFrame
index XD_date
columns XD_date,dividend_per_share,multiplier
(除权除息日,每股分红,分红后每股乘数)
'''
sql_select = '''
SELECT [stockcode]
,[除权除息日]
,[送股比例分子]
,[转增比例分子]
,[派息比例分子_税后]
FROM BasicData.dbo.Yi_Dividend
WHERE stockcode = '%s'
AND [numtime] is not Null
''' % (ticker)
cur.execute(sql_select)
data = cur.fetchall()
columns = [
'ticker', 'XD_date', 'stock_dividend_numerator', 'transfer_numerator',
'cash_dividend_numerator_after_tax'
]
df = pd.DataFrame(data, columns=columns)
df = df.fillna(0)
df['dividend_per_share'] = convert_to_float(
df[u'cash_dividend_numerator_after_tax']) / 10.0
df['multiplier'] = 1 + (convert_to_float(df[u'stock_dividend_numerator']) + \
convert_to_float(df[u'transfer_numerator'])) / 10.0
df['XD_date'] = matlab_time_convert(df['XD_date'])
df = df[['XD_date', 'dividend_per_share',
'multiplier']].set_index('XD_date', drop=False)
df = df.sort_index()
df = df[start_date:end_date]
return df
def __init__(self, elem_lst):
self.cons_no = elem_lst[1] #用户编号（关联主键）
self.cons_id = elem_lst[0] #用户标识
self.cons_sort_code = elem_lst[10] #用户分类
if elem_lst[10] not in sort_dict:
self.cons_sort_code = "others"
self.contract_cap = None #合同容量
self.contract_cap = utils.convert_to_float(elem_lst[5])
self.elec_addr = elem_lst[2] #用电地址
self.elec_type_code = elem_lst[4] #用电类别
self.hec_industry_code = elem_lst[7] #高耗能行业类别
if len(elem_lst[7]) == 0:
self.hec_industry_code = "null"
self.load_attr_code = elem_lst[6] #负荷性质
if len(elem_lst[6]) == 0:
self.load_attr_code = "null"
self.org_no = elem_lst[9] #供电单位编号
self.status_code = elem_lst[8] #用户状态
if len(elem_lst[8]) == 0:
self.status_code = "null"
self.trade_code = elem_lst[3] #行业分类
if elem_lst[3] not in trade_dict:
self.trade_code = "others"
self.urban_rurl_flag = elem_lst[11] #城乡类别
if len(elem_lst[11]) == 0:
self.urban_rurl_flag = "null"
def read_stage_length(stage_soup):
## remove all non alphanumeric, unicode safe
stage_info = stage_soup.find('div', class_='entryHeader').find('h2')
stage_length = convert_to_float(
stage_info.find_all('span')[2].text.replace('(', '').replace(
')', '').replace('k', ''))
return stage_length
def main():
dirname = os.path.dirname(__file__)
output_dirname = os.path.join(dirname, 'results')
try:
os.stat(output_dirname)
except:
os.mkdir(output_dirname)
file_name = sys.argv[1]
dirname = os.path.dirname(__file__)
file_name = os.path.join(dirname, file_name)
d = DataSet(file_name)
d.loadDataSet()
to_remove = [
d.data_set[0].index('Index'),
d.data_set[0].index('First Name'),
d.data_set[0].index('Last Name'),
d.data_set[0].index('Birthday'),
d.data_set[0].index('Best Hand'),
d.data_set[0].index('Hogwarts House'),
# Tests 7/10/18
d.data_set[0].index('Arithmancy'),
d.data_set[0].index('Defense Against the Dark Arts'),
d.data_set[0].index('Divination'),
d.data_set[0].index('Muggle Studies'),
d.data_set[0].index('History of Magic'),
d.data_set[0].index('Transfiguration'),
d.data_set[0].index('Potions'),
d.data_set[0].index('Care of Magical Creatures'),
d.data_set[0].index('Charms'),
d.data_set[0].index('Flying'),
]
X = np.array([[
d.data_set[i][j] for j in range(len(d.data_set[0]))
if j not in to_remove
] for i in range(len(d.data_set))])
#features = X[0,:]
X = convert_to_float(X[1:, ])
y_col_nb = d.data_set[0].index('Hogwarts House')
y = np.array(d.extractColumn(y_col_nb)[1:])
m = MeanImputation(X)
m.train()
m.transform()
sc = Scaling(X)
sc.train()
sc.transform()
l = LogisticRegression(X=X, y=y)
l.train()
def _get_value(self):
"""Parse values from tbl_row, last two cells in row."""
value_1945 = None
value_1946 = None
# if cant convert to float, is missing
try:
value_1945 = convert_to_float(self.row[3])
except:
pass
# if cant convert to float, is missing
try:
value_1946 = convert_to_float(self.row[4])
except:
pass
return [value_1945, value_1946]
def _get_quantity(self):
"""Parse quantities from tbl_row, first two cells after country name."""
quantity_1945 = None
quantity_1946 = None
# if cant convert to float, is missing
try:
quantity_1945 = convert_to_float(self.row[1])
except:
pass
# if cant convert to float, is missing
try:
quantity_1946 = convert_to_float(self.row[2])
except:
pass
return [quantity_1945, quantity_1946]
def get_trial_metadata_dictionaries_partial(self, experiment_number, experimentdict):
'''This creates a dictionary of dictionaries that is organized as such: {Trial-#:{'evid': 12345, 'magnitude': 4.02, 'distance': 124}}.
This makes it much easier for the information stored to be parsed through by utilizing a double index to get the specific piece of
of information about the specific Trial.'''
experimentId = experiment_id[experiment_number]
cache_evid_dict = {}
cache_ml_dict = {}
cache_distance_dict = {}
for trial in experimentdict:
requestDict = self.make_request("GET","/REST/Project/353/Experiment/%s/Trial/%s" % (experimentId, experimentdict[trial]))
data = requestDict['data']
evid = utils.parse_description('evid:', data)
magnitude = utils.parse_description('ml:', data)
distance = utils.parse_description('distance:', data)
cache_evid_dict[trial] = utils.convert_to_long(evid)
cache_ml_dict[trial] = utils.convert_to_float(magnitude)
cache_distance_dict[trial] = utils.convert_to_float(distance)
nees_logging.log_cache_invalid_cache_variables(trial, cache_evid_dict[trial],cache_ml_dict[trial],cache_distance_dict[trial])
return cache_evid_dict, cache_ml_dict, cache_distance_dict
def __init__(self, elem_lst):
self.cons_no = elem_lst[0] #用户编号
self.ymrcvbl_ym = None #应收年月
self.ymrcvbl_ym = utils.convert_to_date_YM('09_ARC_A_RCVBL_FLOW.TSV',
elem_lst[1])
self.org_no = elem_lst[2] #供电单位编号
self.pay_code = elem_lst[3] #缴费方式
self.t_pq = 0.0 #总电量
self.t_pq = utils.convert_to_float(elem_lst[4])
self.rcvbl_amt = 0.0 #应收金额
self.rcvbl_amt = utils.convert_to_float(elem_lst[5])
self.rcved_amt = 0.0 #实收金额
self.rcved_amt = utils.convert_to_float(elem_lst[6])
self.status_code = elem_lst[7] #费用状态
self.rcvbl_penalty = 0.0 #应收违约金
self.rcvbl_penalty = utils.convert_to_float(elem_lst[8])
self.rcved_penalty = 0.0 #实收违约金
self.rcved_penalty = utils.convert_to_float(elem_lst[9])
self.risk_level_code = elem_lst[10] #风险等级
self.owe_amt = 0.0 #电费金额
self.owe_amt = utils.convert_to_float(elem_lst[11])
self.cons_sort_code = elem_lst[12] #用户分类
self.elec_type_code = elem_lst[13] #用电类别
self.ctl_mode = elem_lst[14] #费控方式
def get_trial_metadata_dictionaries_partial(project_id, experiment_id, experimentdict):
'''This creates a dictionary of dictionaries that is organized as such: {Trial-#:{'evid': 12345, 'magnitude': 4.02, 'distance': 124}}.
This makes it much easier for the information stored to be parsed through by utilizing a double index to get the specific piece of
of information about the specific Trial.'''
cache_evid_dict = {}
cache_ml_dict = {}
cache_distance_dict = {}
for trial in experimentdict:
request = "%s%s/Experiment/%s/Trial/%s" % (neeshub_project_path,
project_id,
experiment_id,
experimentdict[trial])
authentic_request = utils.authenticate_request(request)
requestDict = conn.request('GET', authentic_request)
data = requestDict['data']
evid = utils.parse_description('evid:', data)
magnitude = utils.parse_description('ml:', data)
distance = utils.parse_description('distance:', data)
cache_evid_dict[trial] = utils.convert_to_long(evid)
cache_ml_dict[trial] = utils.convert_to_float(magnitude)
cache_distance_dict[trial] = utils.convert_to_float(distance)
nees_logging.log_cache_invalid_cache_variables(trial, cache_evid_dict[trial],cache_ml_dict[trial],cache_distance_dict[trial])
return cache_evid_dict, cache_ml_dict, cache_distance_dict
def standardize_value(self, cleansed_dict, ingredient_texts):
uom_indxs = [
i for i, v in enumerate(cleansed_dict['tokens'])
if v['type'] == 'unit_of_measure'
]
for indx, uom_indx in enumerate(uom_indxs):
try:
uom = cleansed_dict['tokens'][uom_indx]['standard_token']
ing = ingredient_texts[indx]
# Unit of measure is mostly the previous token
# So taking uom_value index as 1 less than uom index
uom_value_indx = uom_indx - 1
value = cleansed_dict['tokens'][uom_value_indx][
'standard_token']
vtype = cleansed_dict['tokens'][uom_value_indx]['type']
if vtype != 'value':
# Getting the previous token if the current token
# is not of type "value"
uom_value_indx = uom_value_indx - 1
if cleansed_dict['tokens'][uom_value_indx][
'type'] == 'value':
value = cleansed_dict['tokens'][uom_value_indx][
'standard_token']
else:
continue
if not value:
continue
sku = ing + '_' + uom
std_values_dict = self.valid_skus.get(sku, {})
std_values = sorted(std_values_dict.keys())
float_value = convert_to_float(value)
if not float_value:
continue
if float_value not in std_values:
for i, v in enumerate(std_values):
if float_value < v:
v = std_values_dict[v]
uom_dict = cleansed_dict['tokens'][uom_value_indx]
uom_dict["standard_token"] = v
if indx == 0:
cleansed_dict['unit_of_measure'] = uom
cleansed_dict['unit_of_measure_value'] = v
break
except IndexError:
continue
return cleansed_dict
def standardize_value_old(self, cleansed_dict, ingredient_texts):
ingredient = cleansed_dict['ingredient']
uom = cleansed_dict['unit_of_measure']
value = cleansed_dict['unit_of_measure_value']
if not value:
return cleansed_dict
sku = ingredient + '_' + uom
std_values_dict = self.valid_skus.get(sku, {})
std_values = sorted(std_values_dict.keys())
float_value = convert_to_float(value)
if float_value not in std_values:
for i, v in enumerate(std_values):
if float_value < v:
value = std_values_dict[v]
break
if cleansed_dict['unit_of_measure_value'] != value:
uom_indxs = [
i for i, v in enumerate(cleansed_dict['tokens'])
if v['type'] == 'unit_of_measure'
]
for i, uom_indx in enumerate(uom_indxs):
try:
uom = cleansed_dict['tokens'][uom_indx]['standard_token']
ing = ingredient_texts[i]
if sku == (ing + '_' + uom):
uom_value_indx = uom_indx - 1
uom_dict = cleansed_dict['tokens'][uom_value_indx]
uom_dict["standard_token"] = value
cleansed_dict['tokens'][uom_value_indx] = uom_dict
if i == 0:
cleansed_dict['unit_of_measure_value'] = value
except IndexError:
break
return cleansed_dict
def _make_profit_statements(self, code, years):
self.profits = ts.get_profit_statement(code)
self.profit_statements = {
year: utils.convert_to_float(self.profits[year])
for year in years
}
def main():
'''
Use this script to run experiments and fine-tune the algoritms
'''
# Load the dataset
file_name = sys.argv[1]
dirname = os.path.dirname(__file__)
file_name = os.path.join(dirname, file_name)
d = DataSet(file_name)
d.loadDataSet()
# Remove useless features (not numeric + bad regressors).
to_remove = [
d.data_set[0].index('Index'),
d.data_set[0].index('First Name'),
d.data_set[0].index('Last Name'),
d.data_set[0].index('Birthday'),
d.data_set[0].index('Best Hand'),
d.data_set[0].index('Hogwarts House'),
# Tests 7/10/18
d.data_set[0].index('Arithmancy'),
d.data_set[0].index('Defense Against the Dark Arts'),
d.data_set[0].index('Divination'),
d.data_set[0].index('Muggle Studies'),
d.data_set[0].index('History of Magic'),
d.data_set[0].index('Transfiguration'),
d.data_set[0].index('Potions'),
d.data_set[0].index('Care of Magical Creatures'),
d.data_set[0].index('Charms'),
d.data_set[0].index('Flying'),
]
X = np.array([[
d.data_set[i][j] for j in range(len(d.data_set[0]))
if j not in to_remove
] for i in range(len(d.data_set))])
X = convert_to_float(X[1:, ])
y_col_nb = d.data_set[0].index('Hogwarts House')
y = np.array(d.extractColumn(y_col_nb)[1:])
# Impute missing values
m = MeanImputation(X)
m.train()
m.transform()
# Scale the variables
sc = Scaling(X)
sc.train()
sc.transform()
# Split the dataset in a training and testing set
sp = SplitTrainTest(X, y)
sp.Split()
X_train = sp.X_train
y_train = sp.y_train
X_test = sp.X_test
y_test = sp.y_test
# Train a logistic regression model
l = LogisticRegression(X=X_train, y=y_train)
l.train()
# Compute the confusion matrix over the training set
y_predicted = l.predict()
cm1 = ConfusionMatrix(y_train, y_predicted)
cm1.getMatrix()
print('\n\n')
print(
'**************** Confusion Matrix on the training set ****************'
)
print('\n')
cm1.Print()
# Compute the confusion matrix over the testing set
y_predicted = l.predict(X_test)
cm2 = ConfusionMatrix(y_test, y_predicted, cm1.unique_labels)
cm2.getMatrix()
print('\n\n')
print(
'**************** Confusion Matrix on the testing set ****************'
)
print('\n')
cm2.Print()
def main():
file_name = sys.argv[1]
dirname = os.path.dirname(__file__)
file_name = os.path.join(dirname, file_name)
d = DataSet(file_name)
d.loadDataSet()
to_remove = [
d.data_set[0].index('Index'),
d.data_set[0].index('First Name'),
d.data_set[0].index('Last Name'),
d.data_set[0].index('Birthday'),
d.data_set[0].index('Best Hand'),
d.data_set[0].index('Hogwarts House'),
# Tests 7/10/18
d.data_set[0].index('Arithmancy'),
d.data_set[0].index('Defense Against the Dark Arts'),
d.data_set[0].index('Divination'),
d.data_set[0].index('Muggle Studies'),
d.data_set[0].index('History of Magic'),
d.data_set[0].index('Transfiguration'),
d.data_set[0].index('Potions'),
d.data_set[0].index('Care of Magical Creatures'),
d.data_set[0].index('Charms'),
d.data_set[0].index('Flying'),
]
X = np.array([[
d.data_set[i][j] for j in range(len(d.data_set[0]))
if j not in to_remove
] for i in range(len(d.data_set))])
X = convert_to_float(X[1:, ])
y_col_nb = d.data_set[0].index('Hogwarts House')
y = np.array(d.extractColumn(y_col_nb)[1:])
m = MeanImputation(X)
m.train()
m.transform()
sc = Scaling(X)
sc.train()
sc.transform()
sp = SplitTrainTest(X, y)
sp.Split()
X_train = sp.X_train
y_train = sp.y_train
X_test = sp.X_test
y_test = sp.y_test
l = LogisticRegression(X=X_train,
y=y_train,
optimizer='sgd',
optimizer_params={
'alpha': 0.5,
'n': 5,
'batch_size': 16
})
l.train()
y_predicted = l.predict()
cm1 = ConfusionMatrix(y_train, y_predicted)
cm1.getMatrix()
print('\n\n')
print(
'**************** Confusion Matrix on the training set ****************'
)
print('\n')
cm1.Print()
y_predicted = l.predict(X_test)
cm2 = ConfusionMatrix(y_test, y_predicted, cm1.unique_labels)
cm2.getMatrix()
print('\n\n')
print(
'**************** Confusion Matrix on the testing set ****************'
)
print('\n')
cm2.Print()
def latest_equity(self):
bs = utils.convert_to_float(self.balance_sheet.balances.iloc[:, 1])
return bs[bsheet.balance_sheet_index['equity']]
import pandas as pd
import numpy as np
from utils import convert_ids, convert_ids, convert_to_float, to_json
movies_metadata_df1 = pd.read_csv('../data/movies_metadata.csv'
, converters={ 'id': lambda x: convert_ids(x)
, 'imdb_id': lambda x: convert_ids(x)
,'popularity': lambda x: convert_to_float(x)
,'genres': lambda x: to_json(x)}
, usecols=['id', 'original_title'
, 'genres' #'homepage'
, 'overview', 'popularity', 'poster_path'
, 'release_date', 'revenue', 'runtime'
, 'spoken_languages', 'title'
, 'vote_average', 'vote_count']
, dtype={'populariy': np.float64}
, parse_dates=True, low_memory=False)
movies_lookup_df = pd.read_csv('../data/movies_metadata.csv'
, converters={'id': lambda x: convert_ids(x), 'imdb_id': lambda x: convert_ids(x)}
,usecols=['id', 'title'], low_memory=False)
#####################################
##SVD DATA SET
movies_df = pd.read_csv('../data/movies_metadata.csv'
, converters={'id': lambda x: convert_ids(x), 'imdb_id': lambda x: convert_ids(x)}
,usecols=['id', 'original_title', 'belongs_to_collection'
, 'budget', 'genres', 'homepage'
,'imdb_id', 'overview', 'popularity', 'poster_path'
, 'production_companies','release_date', 'revenue', 'runtime',
'spoken_languages', 'status', 'tagline', 'title', 'video',
def test_convert_to_float():
assert utils.convert_to_float("23.45") == 23.45
assert utils.convert_to_float("0") == 0.0
assert utils.convert_to_float("-0") == 0.0
assert utils.convert_to_float("-23") == -23.0
assert utils.convert_to_float(245) == 245.0
assert utils.convert_to_float(-245) == -245.0
assert utils.convert_to_float(-245.8457) == -245.8457
assert utils.convert_to_float(0) == 0.0
assert utils.convert_to_float("43.53") == 43.53
assert utils.convert_to_float("25sn") is None
assert utils.convert_to_float("s45") is None
assert utils.convert_to_float("string") is None
def main():
dirname = os.path.dirname(__file__)
dirname_prediction = os.path.join(dirname, 'results')
file_name = sys.argv[1]
file_name = os.path.join(dirname, file_name)
d = DataSet(file_name)
d.loadDataSet()
to_remove = [
d.data_set[0].index('Index'),
d.data_set[0].index('First Name'),
d.data_set[0].index('Last Name'),
d.data_set[0].index('Birthday'),
d.data_set[0].index('Best Hand'),
d.data_set[0].index('Hogwarts House'),
# Tests 7/10/18
d.data_set[0].index('Arithmancy'),
d.data_set[0].index('Defense Against the Dark Arts'),
d.data_set[0].index('Divination'),
d.data_set[0].index('Muggle Studies'),
d.data_set[0].index('History of Magic'),
d.data_set[0].index('Transfiguration'),
d.data_set[0].index('Potions'),
d.data_set[0].index('Care of Magical Creatures'),
d.data_set[0].index('Charms'),
d.data_set[0].index('Flying'),
]
index_position = d.data_set[0].index('Index')
indexes = np.array(
[d.data_set[i][index_position] for i in range(len(d.data_set))])[1:]
X = np.array([[
d.data_set[i][j] for j in range(len(d.data_set[0]))
if j not in to_remove
] for i in range(len(d.data_set))])
#features = X[0,:]
X = convert_to_float(X[1:, ])
m = MeanImputation(X,
path_to_mean_imputation=os.path.join(
dirname_prediction, 'mean_imputation.json'))
m.transform()
sc = Scaling(X,
path_to_scaling=os.path.join(dirname_prediction,
'scaling.json'))
sc.transform()
l = LogisticRegression(X=X,
path_to_beta=os.path.join(dirname_prediction,
'beta.json'))
predictions = l.predict()
dirname = os.path.dirname(__file__)
file_name = os.path.join(dirname, 'resources/houses.csv')
with open(file_name, 'w+') as outfile:
writer = csv.writer(outfile, delimiter=',')
writer.writerow(['Index', 'Hogwarts House'])
for i in range(len(indexes)):
writer.writerow([indexes[i], predictions[i]])
def _make_cash_flows(self, code, years):
cash_flows = ts.get_cash_flow(code)
self.cash_flows = {
year: utils.convert_to_float(cash_flows[year])
for year in years
}
def _make_balance_sheets(self, code, years):
self.balances = ts.get_balance_sheet(code)
self.balance_sheets = {
year: utils.convert_to_float(self.balances[year])
for year in years
}