def read(self):
data = []
for indicator in self.symbols:
# Build URL for api call
try:
df = self._read_one_data(self.url + indicator, self.params)
df.columns = ['country', 'iso_code', 'year', indicator]
data.append(df)
except ValueError as e:
msg = str(e) + ' Indicator: ' + indicator
if self.errors == 'raise':
raise ValueError(msg)
elif self.errors == 'warn':
warnings.warn(msg)
# Confirm we actually got some data, and build Dataframe
if len(data) > 0:
out = reduce(lambda x, y: x.merge(y, how='outer'), data)
out = out.drop('iso_code', axis=1)
out = out.set_index(['country', 'year'])
if PANDAS_0170:
out = out.apply(pd.to_numeric, errors='ignore')
else:
# deprecated in 0.17.0
out = out.convert_objects(convert_numeric=True)
return out
else:
msg = "No indicators returned data."
raise ValueError(msg)
def read(self):
data = []
for indicator in self.symbols:
# Build URL for api call
try:
df = self._read_one_data(self.url + indicator, self.params)
df.columns = ['country', 'iso_code', 'year', indicator]
data.append(df)
except ValueError as e:
msg = str(e) + ' Indicator: ' + indicator
if self.errors == 'raise':
raise ValueError(msg)
elif self.errors == 'warn':
warnings.warn(msg)
# Confirm we actually got some data, and build Dataframe
if len(data) > 0:
out = reduce(lambda x, y: x.merge(y, how='outer'), data)
out = out.drop('iso_code', axis=1)
out = out.set_index(['country', 'year'])
if PANDAS_0170:
out = out.apply(pd.to_numeric, errors='ignore')
else:
# deprecated in 0.17.0
out = out.convert_objects(convert_numeric=True)
return out
else:
msg = "No indicators returned data."
raise ValueError(msg)
def _result_type_many(*arrays_and_dtypes):
""" wrapper around numpy.result_type which overcomes the NPY_MAXARGS (32)
argument limit """
try:
return np.result_type(*arrays_and_dtypes)
except ValueError:
# we have > NPY_MAXARGS terms in our expression
return reduce(np.result_type, arrays_and_dtypes)
def table_view(request):
if request.method == 'POST':
algo_name = request.POST['algo_name']
if not algo_name:
return HttpResponse(
'<h1>Please go back and enter a algo_name</h1>')
signal = request.POST['signal']
if not signal:
return HttpResponse(
'<h1>Please go back and enter a stock signal</h1>')
trade = request.POST['trade']
if not trade:
return HttpResponse(
'<h1>Please go back and enter a stock trade</h1>')
ticker = request.POST['ticker']
if not ticker:
return HttpResponse(
'<h1>Please go back and enter a stock ticker</h1>')
api_url = "https://api.iextrading.com/1.0/stock/{ticker}/chart/1y".format(
ticker=ticker)
headers = {
'User-Agent':
'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.95 Safari/537.36'
}
response = requests.request('GET', api_url, headers=headers)
if response.status_code == 200:
json_response = json.loads(response.content)
else:
return render(
request,
'stocks/errors.html',
context={'error_string_exp': 'Some Errors Occurred!'})
prices = [d['close'] for d in json_response if 'close' in d]
positions, PnL = algo_result(signal, trade, prices)
# Save the Algo name, the daily PnL and the positions.
new_algo = AlgoProp(name=algo_name,
daily_pnl=' '.join(map(str, PnL)),
position=' '.join(map(str, positions)))
new_algo.save()
return_list = list()
val = AlgoProp.objects.all()
for v in val:
l = list(map(float, v.daily_pnl.split(' ')))
avg = reduce(lambda x, y: x + y, l) / len(l)
return_list.append(dict({'daily_pnl': avg, 'name': v.name}))
return render(request, 'stocks/table_view.html', {'d_val': return_list})
def same_as(self, na):
# 截图
fw = open('screenshot_path', 'w', encoding='utf8') # 打开文件写入
fr = open('screenshot_path', 'r', encoding='utf8') # 打开文件读取
t1 = time.strftime('%Y%m%d%H%M',
time.localtime(time.time())) # 获取当前的时间
print('当前时间：' + t1)
open('result', 'a', encoding='utf8').writelines('当前时间：' + t1 + '\n')
# #day = t1[0:8]
day = t1
img_folder = os.path.abspath(
os.path.join(os.path.dirname(__file__),
"..")) + '\\baoxian\\za_40手机资金安全险'
# # 设定文件保存的路径，存放到当前目录下是screenshots文件夹中
# print('当前的路径：' + img_folder)
#open('result', 'a', encoding='utf8').writelines('当前的路径：' + img_folder + '\n')
cre_file = ClassMethon()
cre_file.creat_file(img_folder)
screen_save_path = img_folder + '/' + na + t1 + '.png' # 截屏图片命名方式
#print('当前截图路径已经名称为：' + screen_save_path)
open('result', 'a',
encoding='utf8').writelines('当前截图路径已经名称为：' + screen_save_path +
'\n')
time.sleep(10) # 休眠十秒等待页面加载完成
self.driver.get_screenshot_as_file(screen_save_path) # 截屏并存在指定的路径下
#print('截图已存')
open('result', 'a', encoding='utf8').writelines('截图已存 \n')
#self.pic_save()
imglist = self.imglist
if len(imglist) > 1:
#这里的 screen_save_path 和 imglist[i] 是同一个张图片
image1 = Image.open(imglist[-2])
image2 = Image.open(imglist[-1])
# 把图像对象转换为直方图数据，存在list h1、h2 中s
h1 = image1.histogram()
h2 = image2.histogram()
result = math.sqrt(
reduce(operator.add, list(map(lambda a, b:
(a - b)**2, h1, h2))) /
len(h1)) #通过方差大小进行计算
print(result)
if result > 5:
# 图像不一致，继续执行下一个下拉截图
print(imglist[-1] + '与' + imglist[-2] + '张图像不一致,继续执行。')
open('result', 'a',
encoding='utf8').writelines(imglist[-1] + '与' +
imglist[-2] + '张图像不一致,继续执行。' +
'\n')
else:
# 图像一致，判断一致原因
print(imglist[-1] + '与' + imglist[-2] + '图像一致')
open('result', 'a',
encoding='utf8').writelines(imglist[-1] + '与' +
imglist[-2] + '图像一致' + '\n')
if self.driver.title != '同花顺保险':
print('跳转地址有误,返回上一张图的位置重新截图')
open('result', 'a',
encoding='utf8').writelines('跳转地址有误,返回上一张图的位置重新截图 \n')
def chain_dot(*matrices):
"""
Returns the dot product of the given matrices.
Parameters
----------
matrices: argument list of ndarray
"""
return reduce(lambda x, y: np.dot(y, x), matrices[::-1])
def filter_property_type(self, queryset, field, value):
data = dict(self.data)
if data[field]:
q_list = map(lambda n: Q(property_type__icontains=n), data[field])
q_list = reduce(lambda a, b: a | b, q_list)
return queryset.filter(q_list)
else:
return queryset
def chain_dot(*matrices):
"""
Returns the dot product of the given matrices.
Parameters
----------
matrices: argument list of ndarray
"""
return reduce(lambda x, y: np.dot(y, x), matrices[::-1])
def fitness(individual, target):
"""
Determine the fitness of an individual. Lower is better.
:param individual: the individual to evaluate
:param target: the sum of numbers that individuals are aiming for
:return:
"""
sum = reduce(add, individual, 0)
return abs(target - sum)
def grade(pop, target):
"""
'Find average fitness for a population.'
:param pop:
:param target:
:return:
"""
summed = reduce(add, (fitness(x, target) for x in pop), 0)
return summed / (len(pop) * 1.0)
def visit_BoolOp(self, node, **kwargs):
def visitor(x, y):
lhs = self._try_visit_binop(x)
rhs = self._try_visit_binop(y)
op, op_class, lhs, rhs = self._possibly_transform_eq_ne(node, lhs,
rhs)
return self._possibly_evaluate_binop(op, node.op, lhs, rhs)
operands = node.values
return reduce(visitor, operands)
def _result_type_many(*arrays_and_dtypes):
""" wrapper around numpy.result_type which overcomes the NPY_MAXARGS (32)
argument limit """
try:
return np.result_type(*arrays_and_dtypes)
except ValueError:
# length 0 or length > NPY_MAXARGS both throw a ValueError, so check
# which one we're dealing with
if len(arrays_and_dtypes) == 0:
raise ValueError('at least one array or dtype is required')
return reduce(np.result_type, arrays_and_dtypes)
def visit_BoolOp(self, node, **kwargs):
def visitor(x, y):
lhs = self._try_visit_binop(x)
rhs = self._try_visit_binop(y)
op, op_class, lhs, rhs = self._possibly_transform_eq_ne(
node, lhs, rhs)
return self._possibly_evaluate_binop(op, node.op, lhs, rhs)
operands = node.values
return reduce(visitor, operands)
def __init__(self,
gbls=None,
lcls=None,
level=1,
resolvers=None,
target=None):
self.level = level
self.resolvers = tuple(resolvers or [])
self.globals = dict()
self.locals = dict()
self.target = target
self.ntemps = 1 # number of temporary variables in this scope
if isinstance(lcls, Scope):
ld, lcls = lcls, dict()
self.locals.update(ld.locals.copy())
self.globals.update(ld.globals.copy())
self.resolvers += ld.resolvers
if ld.target is not None:
self.target = ld.target
self.update(ld.level)
frame = sys._getframe(level)
try:
self.globals.update(gbls or frame.f_globals)
self.locals.update(lcls or frame.f_locals)
finally:
del frame
# add some useful defaults
self.globals['Timestamp'] = pd.lib.Timestamp
self.globals['datetime'] = datetime
# SUCH a hack
self.globals['True'] = True
self.globals['False'] = False
# function defs
self.globals['list'] = list
self.globals['tuple'] = tuple
res_keys = (list(o.keys()) for o in self.resolvers)
self.resolver_keys = frozenset(reduce(operator.add, res_keys, []))
self._global_resolvers = self.resolvers + (self.locals, self.globals)
self._resolver = None
self.resolver_dict = {}
for o in self.resolvers:
self.resolver_dict.update(dict(o))
def _format_header(self):
if isinstance(self.columns, MultiIndex):
gen = self._format_header_mi()
else:
gen = self._format_header_regular()
gen2 = ()
if self.df.index.names:
row = [x if x is not None else ''
for x in self.df.index.names] + [''] * len(self.columns)
if reduce(lambda x, y: x and y, map(lambda x: x != '', row)):
gen2 = (ExcelCell(self.rowcounter, colindex, val, header_style)
for colindex, val in enumerate(row))
self.rowcounter += 1
return itertools.chain(gen, gen2)
def _format_header(self):
if isinstance(self.columns, MultiIndex):
gen = self._format_header_mi()
else:
gen = self._format_header_regular()
gen2 = ()
if self.df.index.names:
row = [x if x is not None else ''
for x in self.df.index.names] + [''] * len(self.columns)
if reduce(lambda x, y: x and y, map(lambda x: x != '', row)):
gen2 = (ExcelCell(self.rowcounter, colindex, val, header_style)
for colindex, val in enumerate(row))
self.rowcounter += 1
return itertools.chain(gen, gen2)
def __init__(self, gbls=None, lcls=None, level=1, resolvers=None,
target=None):
self.level = level
self.resolvers = tuple(resolvers or [])
self.globals = dict()
self.locals = dict()
self.target = target
self.ntemps = 1 # number of temporary variables in this scope
if isinstance(lcls, Scope):
ld, lcls = lcls, dict()
self.locals.update(ld.locals.copy())
self.globals.update(ld.globals.copy())
self.resolvers += ld.resolvers
if ld.target is not None:
self.target = ld.target
self.update(ld.level)
frame = sys._getframe(level)
try:
self.globals.update(gbls or frame.f_globals)
self.locals.update(lcls or frame.f_locals)
finally:
del frame
# add some useful defaults
self.globals['Timestamp'] = pd.lib.Timestamp
self.globals['datetime'] = datetime
# SUCH a hack
self.globals['True'] = True
self.globals['False'] = False
# function defs
self.globals['list'] = list
self.globals['tuple'] = tuple
res_keys = (list(o.keys()) for o in self.resolvers)
self.resolver_keys = frozenset(reduce(operator.add, res_keys, []))
self._global_resolvers = self.resolvers + (self.locals, self.globals)
self._resolver = None
self.resolver_dict = {}
for o in self.resolvers:
self.resolver_dict.update(dict(o))
def download(
country=["MX", "CA", "US"], indicator=["NY.GDP.MKTP.CD", "NY.GNS.ICTR.ZS"], start=2003, end=2005, errors="warn"
):
"""
Download data series from the World Bank's World Development Indicators
Parameters
----------
indicator: string or list of strings
taken from the ``id`` field in ``WDIsearch()``
country: string or list of strings.
``all`` downloads data for all countries
2 or 3 character ISO country codes select individual
countries (e.g.``US``,``CA``) or (e.g.``USA``,``CAN``). The codes
can be mixed.
The two ISO lists of countries, provided by wikipedia, are hardcoded
into pandas as of 11/10/2014.
start: int
First year of the data series
end: int
Last year of the data series (inclusive)
errors: str {'ignore', 'warn', 'raise'}, default 'warn'
Country codes are validated against a hardcoded list. This controls
the outcome of that validation, and attempts to also apply
to the results from world bank.
errors='raise', will raise a ValueError on a bad country code.
Returns
-------
``pandas`` DataFrame with columns: country, iso_code, year,
indicator value.
"""
if type(country) == str:
country = [country]
bad_countries = np.setdiff1d(country, country_codes)
# Validate the input
if len(bad_countries) > 0:
tmp = ", ".join(bad_countries)
if errors == "raise":
raise ValueError("Invalid Country Code(s): %s" % tmp)
if errors == "warn":
warnings.warn("Non-standard ISO country codes: %s" % tmp)
# Work with a list of indicators
if type(indicator) == str:
indicator = [indicator]
# Download
data = []
bad_indicators = {}
for ind in indicator:
one_indicator_data, msg = _get_data(ind, country, start, end)
if msg == "Success":
data.append(one_indicator_data)
else:
bad_indicators[ind] = msg
if len(bad_indicators.keys()) > 0:
bad_ind_msgs = [i + " : " + m for i, m in bad_indicators.items()]
bad_ind_msgs = "\n\n".join(bad_ind_msgs)
bad_ind_msgs = "\n\nInvalid Indicators:\n\n%s" % bad_ind_msgs
if errors == "raise":
raise ValueError(bad_ind_msgs)
if errors == "warn":
warnings.warn(bad_ind_msgs)
# Confirm we actually got some data, and build Dataframe
if len(data) > 0:
out = reduce(lambda x, y: x.merge(y, how="outer"), data)
out = out.drop("iso_code", axis=1)
out = out.set_index(["country", "year"])
if PD017:
kwargs = dict((kw, True) for kw in ("datetime", "numeric", "timedelta"))
else:
kwargs = {"convert_numeric": True}
out = out.convert_objects(**kwargs)
return out
else:
msg = "No indicators returned data."
if errors == "ignore":
msg += " Set errors='warn' for more information."
raise ValueError(msg)
def _excel2num(x):
"Convert Excel column name like 'AB' to 0-based column index"
return reduce(lambda s, a: s * 26 + ord(a) - ord('A') + 1,
x.upper().strip(), 0) - 1
def colrename(x):
reps = ('.', '_'), (' ', '_'), ('(', ''), (')', ''), ('{', ''), (
'}', ''), ('\\n', ''), ('\n', ''), ('\\t', ''), ('\t', ''), ('=', '')
return reduce(lambda a, kv: a.replace(*kv), reps, x)
def compose(*funcs):
"""Compose 2 or more callables"""
assert len(funcs) > 1, "At least 2 callables must be passed to compose"
return reduce(_compose2, funcs)
def download(country=['MX', 'CA', 'US'],
indicator=['GDPPCKD', 'GDPPCKN'],
start=2003,
end=2005):
"""
Download data series from the World Bank's World Development Indicators
Parameters
----------
indicator: string or list of strings
taken from the ``id`` field in ``WDIsearch()``
country: string or list of strings.
``all`` downloads data for all countries
ISO-2 character codes select individual countries (e.g.``US``,``CA``)
start: int
First year of the data series
end: int
Last year of the data series (inclusive)
Returns
-------
``pandas`` DataFrame with columns: country, iso2c, year, indicator value.
"""
# Are ISO-2 country codes valid?
valid_countries = [
"AG", "AL", "AM", "AO", "AR", "AT", "AU", "AZ", "BB", "BD", "BE", "BF",
"BG", "BH", "BI", "BJ", "BO", "BR", "BS", "BW", "BY", "BZ", "CA", "CD",
"CF", "CG", "CH", "CI", "CL", "CM", "CN", "CO", "CR", "CV", "CY", "CZ",
"DE", "DK", "DM", "DO", "DZ", "EC", "EE", "EG", "ER", "ES", "ET", "FI",
"FJ", "FR", "GA", "GB", "GE", "GH", "GM", "GN", "GQ", "GR", "GT", "GW",
"GY", "HK", "HN", "HR", "HT", "HU", "ID", "IE", "IL", "IN", "IR", "IS",
"IT", "JM", "JO", "JP", "KE", "KG", "KH", "KM", "KR", "KW", "KZ", "LA",
"LB", "LC", "LK", "LS", "LT", "LU", "LV", "MA", "MD", "MG", "MK", "ML",
"MN", "MR", "MU", "MW", "MX", "MY", "MZ", "NA", "NE", "NG", "NI", "NL",
"NO", "NP", "NZ", "OM", "PA", "PE", "PG", "PH", "PK", "PL", "PT", "PY",
"RO", "RU", "RW", "SA", "SB", "SC", "SD", "SE", "SG", "SI", "SK", "SL",
"SN", "SR", "SV", "SY", "SZ", "TD", "TG", "TH", "TN", "TR", "TT", "TW",
"TZ", "UA", "UG", "US", "UY", "UZ", "VC", "VE", "VN", "VU", "YE", "ZA",
"ZM", "ZW", "all"
]
if type(country) == str:
country = [country]
bad_countries = np.setdiff1d(country, valid_countries)
country = np.intersect1d(country, valid_countries)
country = ';'.join(country)
# Work with a list of indicators
if type(indicator) == str:
indicator = [indicator]
# Download
data = []
bad_indicators = []
for ind in indicator:
try:
tmp = _get_data(ind, country, start, end)
tmp.columns = ['country', 'iso2c', 'year', ind]
data.append(tmp)
except:
bad_indicators.append(ind)
# Warn
if len(bad_indicators) > 0:
print('Failed to obtain indicator(s): %s' % '; '.join(bad_indicators))
print('The data may still be available for download at '
'http://data.worldbank.org')
if len(bad_countries) > 0:
print('Invalid ISO-2 codes: %s' % ' '.join(bad_countries))
# Merge WDI series
if len(data) > 0:
out = reduce(lambda x, y: x.merge(y, how='outer'), data)
# Clean
out = out.drop('iso2c', axis=1)
out = out.set_index(['country', 'year'])
out = out.convert_objects(convert_numeric=True)
return out
def _excel2num(x):
"Convert Excel column name like 'AB' to 0-based column index"
return reduce(lambda s, a: s * 26 + ord(a) - ord('A') + 1,
x.upper().strip(), 0) - 1
def rfd_selected_to_max_clique(self, current: QTreeWidgetItem, previous: QTreeWidgetItem):
if current:
t0 = time.time()
rfd: RFD = current.data(self.RFD, Qt.UserRole)
self.rfd_subject.on_next(rfd)
# https://stackoverflow.com/questions/38987/how-to-merge-two-dictionaries-in-a-single-expression#26853961
rfd_thresholds: dict = {**rfd.get_left_hand_side(), **rfd.get_right_hand_side()}
lhs = rfd.get_left_hand_side()
rhs = rfd.get_right_hand_side()
lhs_keys = lhs.keys()
rhs_keys = rhs.keys()
# https://stackoverflow.com/questions/1720421/how-to-concatenate-two-lists-in-python#answer-35631185
rfd_columns = [*lhs_keys, *rhs_keys]
rfd_columns_index: dict = {value: position for (position, value) in enumerate(rfd_columns)}
rows, columns = self.data_frame.shape
# Calculate all possible differences.
# This is an O(N^2) operation and may be costly in terms of time and memory.
# dist: ndarray = np.abs(rfd_columns_data[:, None] - rfd_columns_data)
full_dist = DiffDataFrame.full_diff(self.data_frame[rfd_columns])
dist: np.ndarray = np.array(
[[full_dist.iloc[row1 * rows + row2] for row2 in range(0, rows)] for row1 in range(0, rows)])
# Identify the suitable pairs of rows:
# im: ndarray = (dist[:, :, 0] <= 2) & (dist[:, :, 1] <= 0) & (dist[:, :, 2] <= 1)
conditions_arrays: np.ndarray = [(dist[:, :, rfd_columns_index[column]] <= rfd_thresholds[column])
for column in rfd_columns]
adjacency_matrix: np.ndarray = np.array(reduce(lambda a, b: np.bitwise_and(a, b), conditions_arrays))
# Use them as an adjacency matrix and construct a graph.
# The graph nodes represent rows in the original dataframe.
# The nodes are connected if the corresponding rows are in the RFD:
graph = nx.from_numpy_matrix(adjacency_matrix)
max_clique = max(nx.clique.find_cliques(graph), key=len)
df: DataFrame = self.data_frame.loc[max_clique, :]
t1 = time.time()
seconds = t1 - t0
current.setText(self.TIME, str(seconds) + "''")
percentage = round((df.shape[0] / self.rows_count) * 100)
current.setText(self.EXTENT, str(percentage) + "%")
df_indexes = df.index.values.tolist()
# self.pandas_model.update_data(self.data_frame)
'''self.rfd_data_set_table.clearSelection()
def download(country=['MX', 'CA', 'US'], indicator=['GDPPCKD', 'GDPPCKN'],
start=2003, end=2005):
"""
Download data series from the World Bank's World Development Indicators
Parameters
----------
indicator: string or list of strings
taken from the ``id`` field in ``WDIsearch()``
country: string or list of strings.
``all`` downloads data for all countries
ISO-2 character codes select individual countries (e.g.``US``,``CA``)
start: int
First year of the data series
end: int
Last year of the data series (inclusive)
Returns
-------
``pandas`` DataFrame with columns: country, iso2c, year, indicator value.
"""
# Are ISO-2 country codes valid?
valid_countries = ["AG", "AL", "AM", "AO", "AR", "AT", "AU", "AZ", "BB",
"BD", "BE", "BF", "BG", "BH", "BI", "BJ", "BO", "BR", "BS", "BW",
"BY", "BZ", "CA", "CD", "CF", "CG", "CH", "CI", "CL", "CM", "CN",
"CO", "CR", "CV", "CY", "CZ", "DE", "DK", "DM", "DO", "DZ", "EC",
"EE", "EG", "ER", "ES", "ET", "FI", "FJ", "FR", "GA", "GB", "GE",
"GH", "GM", "GN", "GQ", "GR", "GT", "GW", "GY", "HK", "HN", "HR",
"HT", "HU", "ID", "IE", "IL", "IN", "IR", "IS", "IT", "JM", "JO",
"JP", "KE", "KG", "KH", "KM", "KR", "KW", "KZ", "LA", "LB", "LC",
"LK", "LS", "LT", "LU", "LV", "MA", "MD", "MG", "MK", "ML", "MN",
"MR", "MU", "MW", "MX", "MY", "MZ", "NA", "NE", "NG", "NI", "NL",
"NO", "NP", "NZ", "OM", "PA", "PE", "PG", "PH", "PK", "PL", "PT",
"PY", "RO", "RU", "RW", "SA", "SB", "SC", "SD", "SE", "SG", "SI",
"SK", "SL", "SN", "SR", "SV", "SY", "SZ", "TD", "TG", "TH", "TN",
"TR", "TT", "TW", "TZ", "UA", "UG", "US", "UY", "UZ", "VC", "VE",
"VN", "VU", "YE", "ZA", "ZM", "ZW", "all"]
if type(country) == str:
country = [country]
bad_countries = np.setdiff1d(country, valid_countries)
country = np.intersect1d(country, valid_countries)
country = ';'.join(country)
# Work with a list of indicators
if type(indicator) == str:
indicator = [indicator]
# Download
data = []
bad_indicators = []
for ind in indicator:
try:
tmp = _get_data(ind, country, start, end)
tmp.columns = ['country', 'iso2c', 'year', ind]
data.append(tmp)
except:
bad_indicators.append(ind)
# Warn
if len(bad_indicators) > 0:
print('Failed to obtain indicator(s): %s' % '; '.join(bad_indicators))
print('The data may still be available for download at http://data.worldbank.org')
if len(bad_countries) > 0:
print('Invalid ISO-2 codes: %s' % ' '.join(bad_countries))
# Merge WDI series
if len(data) > 0:
out = reduce(lambda x, y: x.merge(y, how='outer'), data)
# Clean
out = out.drop('iso2c', axis=1)
out = out.set_index(['country', 'year'])
out = out.convert_objects(convert_numeric=True)
return out
def download(country=['MX', 'CA', 'US'],
indicator=['NY.GDP.MKTP.CD', 'NY.GNS.ICTR.ZS'],
start=2003,
end=2005,
errors='warn'):
"""
Download data series from the World Bank's World Development Indicators
Parameters
----------
indicator: string or list of strings
taken from the ``id`` field in ``WDIsearch()``
country: string or list of strings.
``all`` downloads data for all countries
2 or 3 character ISO country codes select individual
countries (e.g.``US``,``CA``) or (e.g.``USA``,``CAN``). The codes
can be mixed.
The two ISO lists of countries, provided by wikipedia, are hardcoded
into pandas as of 11/10/2014.
start: int
First year of the data series
end: int
Last year of the data series (inclusive)
errors: str {'ignore', 'warn', 'raise'}, default 'warn'
Country codes are validated against a hardcoded list. This controls
the outcome of that validation, and attempts to also apply
to the results from world bank.
errors='raise', will raise a ValueError on a bad country code.
Returns
-------
``pandas`` DataFrame with columns: country, iso_code, year,
indicator value.
"""
if type(country) == str:
country = [country]
bad_countries = np.setdiff1d(country, country_codes)
# Validate the input
if len(bad_countries) > 0:
tmp = ", ".join(bad_countries)
if errors == 'raise':
raise ValueError("Invalid Country Code(s): %s" % tmp)
if errors == 'warn':
warnings.warn('Non-standard ISO country codes: %s' % tmp)
# Work with a list of indicators
if type(indicator) == str:
indicator = [indicator]
# Download
data = []
bad_indicators = {}
for ind in indicator:
one_indicator_data, msg = _get_data(ind, country, start, end)
if msg == "Success":
data.append(one_indicator_data)
else:
bad_indicators[ind] = msg
if len(bad_indicators.keys()) > 0:
bad_ind_msgs = [i + " : " + m for i, m in bad_indicators.items()]
bad_ind_msgs = "\n\n".join(bad_ind_msgs)
bad_ind_msgs = "\n\nInvalid Indicators:\n\n%s" % bad_ind_msgs
if errors == 'raise':
raise ValueError(bad_ind_msgs)
if errors == 'warn':
warnings.warn(bad_ind_msgs)
# Confirm we actually got some data, and build Dataframe
if len(data) > 0:
out = reduce(lambda x, y: x.merge(y, how='outer'), data)
out = out.drop('iso_code', axis=1)
out = out.set_index(['country', 'year'])
out = out._convert(datetime=True, numeric=True)
return out
else:
msg = "No indicators returned data."
if errors == 'ignore':
msg += " Set errors='warn' for more information."
raise ValueError(msg)
def _compose(*funcs):
"""Compose 2 or more callables"""
assert len(funcs) > 1, 'At least 2 callables must be passed to compose'
return reduce(_compose2, funcs)