def storeHdf5(data, tag, path):
hdf = HDFStore(path,'a')
if tag in hdf.keys():
hdf.append(tag,data)
else:
hdf.put(tag,data)
hdf.close()
class HDFStorePanel(BaseIO):
goal_time = 0.2
def setup(self):
self.fname = '__test__.h5'
with warnings.catch_warnings(record=True):
self.p = Panel(np.random.randn(20, 1000, 25),
items=['Item%03d' % i for i in range(20)],
major_axis=date_range('1/1/2000', periods=1000),
minor_axis=['E%03d' % i for i in range(25)])
self.store = HDFStore(self.fname)
self.store.append('p1', self.p)
def teardown(self):
self.store.close()
self.remove(self.fname)
def time_read_store_table_panel(self):
with warnings.catch_warnings(record=True):
self.store.select('p1')
def time_write_store_table_panel(self):
with warnings.catch_warnings(record=True):
self.store.append('p2', self.p)
class HDFStorePanel(BaseIO):
goal_time = 0.2
def setup(self):
self.fname = '__test__.h5'
with warnings.catch_warnings(record=True):
self.p = Panel(np.random.randn(20, 1000, 25),
items=['Item%03d' % i for i in range(20)],
major_axis=date_range('1/1/2000', periods=1000),
minor_axis=['E%03d' % i for i in range(25)])
self.store = HDFStore(self.fname)
self.store.append('p1', self.p)
def teardown(self):
self.store.close()
self.remove(self.fname)
def time_read_store_table_panel(self):
with warnings.catch_warnings(record=True):
self.store.select('p1')
def time_write_store_table_panel(self):
with warnings.catch_warnings(record=True):
self.store.append('p2', self.p)
def storeHdf5(data, tag, path):
hdf = HDFStore(path, 'a')
if tag in hdf.keys():
hdf.append(tag, data)
else:
hdf.put(tag, data)
hdf.close()
def store_results(self, result, index, columns, hdf5_file):
self.df = DataFrame(result, columns=columns)
self.df = self.df.set_index(index)
self.df.sort_index(inplace=True)
# Store the DataFrame as an HDF5 file...
hdf = HDFStore(hdf5_file)
# Append the dataframe, and ensure addr / host can be 17 chars long
hdf.append('df', self.df, data_columns=list(columns),
min_itemsize={'addr': 17, 'host': 17})
hdf.close()
def test_complibs_default_settings(setup_path):
# GH15943
df = tm.makeDataFrame()
# Set complevel and check if complib is automatically set to
# default value
with ensure_clean_path(setup_path) as tmpfile:
df.to_hdf(tmpfile, "df", complevel=9)
result = read_hdf(tmpfile, "df")
tm.assert_frame_equal(result, df)
with tables.open_file(tmpfile, mode="r") as h5file:
for node in h5file.walk_nodes(where="/df", classname="Leaf"):
assert node.filters.complevel == 9
assert node.filters.complib == "zlib"
# Set complib and check to see if compression is disabled
with ensure_clean_path(setup_path) as tmpfile:
df.to_hdf(tmpfile, "df", complib="zlib")
result = read_hdf(tmpfile, "df")
tm.assert_frame_equal(result, df)
with tables.open_file(tmpfile, mode="r") as h5file:
for node in h5file.walk_nodes(where="/df", classname="Leaf"):
assert node.filters.complevel == 0
assert node.filters.complib is None
# Check if not setting complib or complevel results in no compression
with ensure_clean_path(setup_path) as tmpfile:
df.to_hdf(tmpfile, "df")
result = read_hdf(tmpfile, "df")
tm.assert_frame_equal(result, df)
with tables.open_file(tmpfile, mode="r") as h5file:
for node in h5file.walk_nodes(where="/df", classname="Leaf"):
assert node.filters.complevel == 0
assert node.filters.complib is None
# Check if file-defaults can be overridden on a per table basis
with ensure_clean_path(setup_path) as tmpfile:
store = HDFStore(tmpfile)
store.append("dfc", df, complevel=9, complib="blosc")
store.append("df", df)
store.close()
with tables.open_file(tmpfile, mode="r") as h5file:
for node in h5file.walk_nodes(where="/df", classname="Leaf"):
assert node.filters.complevel == 0
assert node.filters.complib is None
for node in h5file.walk_nodes(where="/dfc", classname="Leaf"):
assert node.filters.complevel == 9
assert node.filters.complib == "blosc"
def store_to_liam(self):
'''
Sauvegarde des données au format utilisé ensuite par le modèle Til
Séléctionne les variables appelée par Til derrière
Appelle des fonctions de Liam2
'''
path = self._output_name()
h5file = tables.openFile(path, mode="w")
ent_node = h5file.createGroup("/", "entities", "Entities")
for ent_name in ['ind', 'foy', 'men', 'futur', 'past']:
entity = eval('self.' + ent_name)
if entity is not None:
entity = entity.fillna(-1)
try:
ent_table = entity.to_records(index=False)
except:
pdb.set_trace()
dtypes = ent_table.dtype
final_name = of_name_to_til[ent_name]
try:
table = h5file.createTable(ent_node, final_name, dtypes, title="%s table" % final_name)
table.append(ent_table)
except:
pdb.set_trace()
table.flush()
if ent_name == 'men':
entity = entity.loc[entity['id']>-1]
ent_table2 = entity[['pond', 'id', 'period']].to_records(index=False)
dtypes2 = ent_table2.dtype
table = h5file.createTable(ent_node, 'companies', dtypes2, title="'companies table")
table.append(ent_table2)
table.flush()
if ent_name == 'ind':
ent_table2 = entity[['agem', 'sexe', 'pere', 'mere', 'id', 'findet', 'period']].to_records(
index = False)
dtypes2 = ent_table2.dtype
table = h5file.createTable(ent_node, 'register', dtypes2, title="register table")
table.append(ent_table2)
table.flush()
h5file.close()
# 3 - table longitudinal
# Note: on conserve le format pandas ici
store = HDFStore(path)
for varname, table in self.longitudinal.iteritems():
table['id'] = table.index
store.append('longitudinal/' + varname, table)
store.close()
def store_results(self, result, index, columns, hdf5_file):
self.df = DataFrame(result, columns=columns)
self.df = self.df.set_index(index)
self.df.sort_index(inplace=True)
# Store the DataFrame as an HDF5 file...
hdf = HDFStore(hdf5_file)
# Append the dataframe, and ensure addr / host can be 17 chars long
hdf.append('df',
self.df,
data_columns=list(columns),
min_itemsize={
'addr': 17,
'host': 17
})
hdf.close()
def pf2pandas(wd, files, vars=None, npwd=None, rmvars=None, \
debug=False):
"""
Read in GEOS-Chem planeflight output and convert to HDF format
- Converts date and time columns to datetime format indexes
- the resultant HDF is in 2D list form
( aka further processing required to 3D /2D output )
Note:
- This function is limited by the csv read speed. for large csv output expect
significant processing times or set to automatically run post run
- Original files are not removed, so this function will double space usage for
output unless the original fiels are deleted.
"""
# Ensure working dorectory string has leading foreward slash
if wd[-1] != '/':
wd += '/'
# pfdate =( re.findall('\d+', file ) )[-1]
if not isinstance(vars, list ):
vars, sites = get_pf_headers( files[0], debug=debug )
if not isinstance(npwd, str ):
npwd = get_dir('npwd')
hdf =HDFStore( npwd+ 'pf_{}_{}.h5'.format( wd.split('/')[-3], \
wd.split('/')[-2], wd.split('/')[-1] ))
if debug:
print hdf
for file in files:
print file#, pfdate
# convert planeflight.log to DataFrame
df = pf_csv2pandas( file, vars )
if file==files[0]:
hdf.put('d1', df, format='table', data_columns=True)
else:
hdf.append('d1', df, format='table', data_columns=True)
if debug:
print hdf['d1'].shape, hdf['d1'].index
del df
hdf.close()
def pf2pandas(wd, files, vars=None, npwd=None, rmvars=None, \
debug=False):
"""
Read in GEOS-Chem planeflight output and convert to HDF format
- Converts date and time columns to datetime format indexes
- the resultant HDF is in 2D list form
( aka further processing required to 3D /2D output )
Note:
- This function is limited by the csv read speed. for large csv output expect
significant processing times or set to automatically run post run
- Original files are not removed, so this function will double space usage for
output unless the original fiels are deleted.
"""
# Ensure working dorectory string has leading foreward slash
if wd[-1] != '/':
wd += '/'
# pfdate =( re.findall('\d+', file ) )[-1]
if not isinstance(vars, list ):
vars, sites = get_pf_headers( files[0], debug=debug )
if not isinstance(npwd, str ):
npwd = get_dir('npwd')
hdf =HDFStore( npwd+ 'pf_{}_{}.h5'.format( wd.split('/')[-3], \
wd.split('/')[-2], wd.split('/')[-1] ))
if debug:
print hdf
for file in files:
print file#, pfdate
# convert planeflight.log to DataFrame
df = pf_csv2pandas( file, vars )
if file==files[0]:
hdf.put('d1', df, format='table', data_columns=True)
else:
hdf.append('d1', df, format='table', data_columns=True)
if debug:
print hdf['d1'].shape, hdf['d1'].index
del df
hdf.close()
def to_frame_hdf(self, store_path, store_key, df_cb=None, max_msg=None,
usecols=None, chunk_cnt=CHUNK_CNT):
"""Convert to Pandas DataFrame and save to HDF then returns
HDFStore."""
store = HDFStore(store_path, 'w')
_c = self._to_frame_prop('to_frame_hdf', False)
for df in self._to_frame_gen(_c, usecols, chunk_cnt):
min_itemsize = {'kind': 20, 'msg': 255}
# pytables not support unicode for now
df['msg'] = df['msg'].apply(lambda m: m.encode('utf8'))
if df_cb is not None:
df_cb(df)
if max_msg is not None:
min_itemsize['msg'] = max_msg
store.append(store_key, df, format='table',
min_itemsize=min_itemsize)
store.flush()
store.close()
_c.pg.done()
def test_open_args(setup_path):
with tm.ensure_clean(setup_path) as path:
df = tm.makeDataFrame()
# create an in memory store
store = HDFStore(
path, mode="a", driver="H5FD_CORE", driver_core_backing_store=0
)
store["df"] = df
store.append("df2", df)
tm.assert_frame_equal(store["df"], df)
tm.assert_frame_equal(store["df2"], df)
store.close()
# the file should not have actually been written
assert not os.path.exists(path)
def csv2hdf5(csv_name, h5_name, dfname, option='frame'):
"""
Convert a csv file to a dataframe in a hdf5
Parameters:
csv_name: string
csv file name
h5_name : string
hdf5 file name
dfname : string
dataframe name
option : string, 'frame' or 'table', default to 'frame'
stoing type in the pytable
"""
table = read_csv(csv_name)
store = HDFStore(h5_name)
if option == 'frame':
store.put(dfname, table)
elif option == 'table': # for frame_table à la pytables
object_cols = table.dtypes[table.dtypes == 'object']
print object_cols.index
try:
store.append(dfname, table)
except:
print table.get_dtype_counts()
object_cols = table.dtypes[table.dtypes == 'object']
for col in object_cols.index:
print 'removing object column :', col
del table[col]
store.append(dfname, table)
print store
store.close()
def csv2hdf5(csv_name, h5_name, dfname, option='frame'):
"""
Convert a csv file to a dataframe in a hdf5
Parameters:
csv_name: string
csv file name
h5_name : string
hdf5 file name
dfname : string
dataframe name
option : string, 'frame' or 'table', default to 'frame'
stoing type in the pytable
"""
table = read_csv(csv_name)
store = HDFStore(h5_name)
if option == 'frame':
store.put(dfname, table)
elif option == 'table': # for frame_table à la pytables
object_cols = table.dtypes[ table.dtypes == 'object']
print object_cols.index
try:
store.append(dfname,table)
except:
print table.get_dtype_counts()
object_cols = table.dtypes[ table.dtypes == 'object']
for col in object_cols.index:
print 'removing object column :', col
del table[col]
store.append(dfname,table)
print store
store.close()
def main(period=None):
temps = time.clock()
input_tab = "C:/openfisca/output/liam/" + "LiamLeg.h5"
output_tab = "C:/Myliam2/Model/SimulTest.h5"
store = HDFStore(input_tab)
goal = HDFStore(output_tab)
name_convertion = {"ind": "person", "foy": "declar", "men": "menage", "fam": "menage"}
# on travaille d'abord sur l'ensemble des tables puis on selectionne chaque annee
# step 1
for ent in ("ind", "men", "foy", "fam"):
dest = name_convertion[ent]
tab_in = store[ent]
tab_out = goal["entities/" + dest]
# on jour sur les variable a garder
# TODO: remonter au niveau de of_on_liam mais la c'est pratique du fait de
# l'autre table
ident = "id" + ent
if ent == "ind":
ident = "noi"
# on garde les valeurs de depart
to_remove = [x for x in tab_in.columns if x in tab_out.columns]
# on retire les identifiant sauf celui qui deviendra id
list_id = ["idmen", "idfoy", "idfam", "id", "quifoy", "quifam", "quimen", "noi"]
list_id.remove(ident)
to_remove = to_remove + [x for x in tab_in.columns if x in list_id]
# on n4oublie pas de garder periode
to_remove.remove("period")
tab_in = tab_in.drop(to_remove, axis=1)
tab_in = tab_in.rename(columns={ident: "id"})
tab_out = merge(tab_in, tab_out, how="right", on=["id", "period"], sort=False)
goal.remove("entities/" + dest)
goal.append("entities/" + dest, tab_out)
# new_tab = np.array(tab_out.to_records())
store.close()
goal.close()
def read_raw_tecplot_case_and_write_pandas_hdf5(
case_folder,
root = 0,
output_file = 0,
serration_angle = 0,
angle_correction = 0,
height_correction = 0,
streamwise_correction = 0,
overwrite = False,
time_step_limit = 0,
airfoil_normal = False,
):
from os.path import isfile,join,splitext
from os import listdir
from progressbar import ProgressBar,Percentage,Bar,ETA,SimpleProgress
from pandas import HDFStore
# File related things ######################################################
if not output_file:
output_file = case_folder+".hdf5"
if airfoil_normal:
output_file = output_file+"_AirfoilNormal"
if not output_file.endswith('.hdf5'):
output_file = output_file.replace(".hdf5","")+".hdf5"
if isfile(output_file) and not overwrite:
print " Exiting; file exists:\n{0}".format(output_file)
return 0
else:
print " Writing\n{0}".format(output_file)
# ##########################################################################
hdf = HDFStore(output_file)
time_step_files = sorted([f for f in listdir(join(root,case_folder)) \
if splitext(f)[1] == '.dat'])
if time_step_limit:
time_step_files = time_step_files[:time_step_limit]
progress = ProgressBar(
widgets=[
Bar(),' ',
Percentage(),' ',
ETA(), ' (file ',
SimpleProgress(),')'],
maxval=len(time_step_files)
).start()
cnt = 0
for f,t in zip(time_step_files,range(len(time_step_files))):
df_t = read_tecplot_file_and_correct_for_location_rotation(
tecplot_file = join(root,case_folder,f),
serration_angle = serration_angle,
angle_correction = angle_correction,
height_correction = height_correction,
streamwise_correction = streamwise_correction,
time_step = t,
airfoil_normal = airfoil_normal,
)
df_t = get_vorticity(df_t)
if cnt == 0:
df = df_t.copy()
else:
df = df.append( df_t, drop_index = True)
#df = df.drop_duplicates()
try:
x_cnt = df.x.value_counts().max()
except AttributeError:
print df
raise
if not x_cnt.max() == x_cnt.min():
print " There's something wrong, counted {0} instances of x"\
.format(x_cnt.max())
return 0
if t == 30:
hdf.put(case_folder,
df.convert_objects(),
format='table', data_columns=True
)
elif cnt == 30 and not t == cnt:
hdf.append(case_folder,
df.convert_objects(),
format='table', data_columns=True
)
cnt = 0
cnt += 1
progress.update(t)
progress.finish()
hdf.close()
return 1
def test_multiple_open_close(setup_path):
# gh-4409: open & close multiple times
with ensure_clean_path(setup_path) as path:
df = tm.makeDataFrame()
df.to_hdf(path, "df", mode="w", format="table")
# single
store = HDFStore(path)
assert "CLOSED" not in store.info()
assert store.is_open
store.close()
assert "CLOSED" in store.info()
assert not store.is_open
with ensure_clean_path(setup_path) as path:
if pytables._table_file_open_policy_is_strict:
# multiples
store1 = HDFStore(path)
msg = (
r"The file [\S]* is already opened\. Please close it before "
r"reopening in write mode\."
)
with pytest.raises(ValueError, match=msg):
HDFStore(path)
store1.close()
else:
# multiples
store1 = HDFStore(path)
store2 = HDFStore(path)
assert "CLOSED" not in store1.info()
assert "CLOSED" not in store2.info()
assert store1.is_open
assert store2.is_open
store1.close()
assert "CLOSED" in store1.info()
assert not store1.is_open
assert "CLOSED" not in store2.info()
assert store2.is_open
store2.close()
assert "CLOSED" in store1.info()
assert "CLOSED" in store2.info()
assert not store1.is_open
assert not store2.is_open
# nested close
store = HDFStore(path, mode="w")
store.append("df", df)
store2 = HDFStore(path)
store2.append("df2", df)
store2.close()
assert "CLOSED" in store2.info()
assert not store2.is_open
store.close()
assert "CLOSED" in store.info()
assert not store.is_open
# double closing
store = HDFStore(path, mode="w")
store.append("df", df)
store2 = HDFStore(path)
store.close()
assert "CLOSED" in store.info()
assert not store.is_open
store2.close()
assert "CLOSED" in store2.info()
assert not store2.is_open
# ops on a closed store
with ensure_clean_path(setup_path) as path:
df = tm.makeDataFrame()
df.to_hdf(path, "df", mode="w", format="table")
store = HDFStore(path)
store.close()
msg = r"[\S]* file is not open!"
with pytest.raises(ClosedFileError, match=msg):
store.keys()
with pytest.raises(ClosedFileError, match=msg):
"df" in store
with pytest.raises(ClosedFileError, match=msg):
len(store)
with pytest.raises(ClosedFileError, match=msg):
store["df"]
with pytest.raises(ClosedFileError, match=msg):
store.select("df")
with pytest.raises(ClosedFileError, match=msg):
store.get("df")
with pytest.raises(ClosedFileError, match=msg):
store.append("df2", df)
with pytest.raises(ClosedFileError, match=msg):
store.put("df3", df)
with pytest.raises(ClosedFileError, match=msg):
store.get_storer("df2")
with pytest.raises(ClosedFileError, match=msg):
store.remove("df2")
with pytest.raises(ClosedFileError, match=msg):
store.select("df")
msg = "'HDFStore' object has no attribute 'df'"
with pytest.raises(AttributeError, match=msg):
store.df
def load_from_store_or_yahoo(start=None, end=None, symbol=None):
append = False
hdf = HDFStore(settings.storage_path)
today = dt.datetime.today().date()
yahoo_symbol = symbol
symbol = clean_symbol(symbol)
# this case, earlier data than in store is requested. The table needs to be rewritten
if symbol in hdf:
df = hdf[symbol]
start_store = df.index.min()
if isinstance(start, str):
start = dt.datetime.strptime(start, '%Y-%m-%d')
if start_store.date() > start:
hdf.remove(symbol)
lprint('start date was earlier than the oldest date in the storage. storage needs to be rewritten.')
if symbol in hdf:
df = hdf[symbol]
end_store = df.index.max()
# check if today is a weekend day
weekday = dt.datetime.today().weekday()
last_trading_day = today
if weekday in [5, 6]:
correction = 1 if weekday == 5 else 2
last_trading_day = today - dt.timedelta(correction)
# if the last trading day is the max date in the store than do not reload data
if last_trading_day == end_store.date():
lprint('loaded %s data from storage.' % symbol)
return df
# if the last trading is younger that the last trading day, load the difference
end = today + dt.timedelta(1)
start = end_store
append = True
# if no store was found, use the start and end from above
df = None
count = 0
while df is None and count < 10:
try:
df = get_yahoo_data(start=start, end=end, symbol=yahoo_symbol)
except RemoteDataError:
time.sleep(10 + int(np.random.rand() * 10))
count += 1
if df is None:
raise Exception('Even after 10 trials data could not be loaded from yahoo')
# remove blanks in the header
df.columns = [x.replace(' ', '_') for x in df.columns]
# store or append to hdf5 storage
if symbol in hdf:
# drop duplicates
exist_df = hdf[symbol]
df = df[~df.index.isin(exist_df.index)]
if append:
hdf.append(symbol, df, format='table', data_columns=True)
else:
df.drop_duplicates(inplace=True)
hdf.put(symbol, df, format='table', data_columns=True)
if not df.index.is_unique:
lprint('index of %s is not unique' % symbol)
return df
class HDFStoreDataFrame(BaseIO):
def setup(self):
N = 25000
index = tm.makeStringIndex(N)
self.df = DataFrame({'float1': np.random.randn(N),
'float2': np.random.randn(N)},
index=index)
self.df_mixed = DataFrame({'float1': np.random.randn(N),
'float2': np.random.randn(N),
'string1': ['foo'] * N,
'bool1': [True] * N,
'int1': np.random.randint(0, N, size=N)},
index=index)
self.df_wide = DataFrame(np.random.randn(N, 100))
self.start_wide = self.df_wide.index[10000]
self.stop_wide = self.df_wide.index[15000]
self.df2 = DataFrame({'float1': np.random.randn(N),
'float2': np.random.randn(N)},
index=date_range('1/1/2000', periods=N))
self.start = self.df2.index[10000]
self.stop = self.df2.index[15000]
self.df_wide2 = DataFrame(np.random.randn(N, 100),
index=date_range('1/1/2000', periods=N))
self.df_dc = DataFrame(np.random.randn(N, 10),
columns=['C%03d' % i for i in range(10)])
self.fname = '__test__.h5'
self.store = HDFStore(self.fname)
self.store.put('fixed', self.df)
self.store.put('fixed_mixed', self.df_mixed)
self.store.append('table', self.df2)
self.store.append('table_mixed', self.df_mixed)
self.store.append('table_wide', self.df_wide)
self.store.append('table_wide2', self.df_wide2)
def teardown(self):
self.store.close()
self.remove(self.fname)
def time_read_store(self):
self.store.get('fixed')
def time_read_store_mixed(self):
self.store.get('fixed_mixed')
def time_write_store(self):
self.store.put('fixed_write', self.df)
def time_write_store_mixed(self):
self.store.put('fixed_mixed_write', self.df_mixed)
def time_read_store_table_mixed(self):
self.store.select('table_mixed')
def time_write_store_table_mixed(self):
self.store.append('table_mixed_write', self.df_mixed)
def time_read_store_table(self):
self.store.select('table')
def time_write_store_table(self):
self.store.append('table_write', self.df)
def time_read_store_table_wide(self):
self.store.select('table_wide')
def time_write_store_table_wide(self):
self.store.append('table_wide_write', self.df_wide)
def time_write_store_table_dc(self):
self.store.append('table_dc_write', self.df_dc, data_columns=True)
def time_query_store_table_wide(self):
self.store.select('table_wide', where="index > self.start_wide and "
"index < self.stop_wide")
def time_query_store_table(self):
self.store.select('table', where="index > self.start and "
"index < self.stop")
def time_store_repr(self):
repr(self.store)
def time_store_str(self):
str(self.store)
def time_store_info(self):
self.store.info()
class HDFStoreDataFrame(BaseIO):
goal_time = 0.2
def setup(self):
N = 25000
index = tm.makeStringIndex(N)
self.df = DataFrame(
{
'float1': np.random.randn(N),
'float2': np.random.randn(N)
},
index=index)
self.df_mixed = DataFrame(
{
'float1': np.random.randn(N),
'float2': np.random.randn(N),
'string1': ['foo'] * N,
'bool1': [True] * N,
'int1': np.random.randint(0, N, size=N)
},
index=index)
self.df_wide = DataFrame(np.random.randn(N, 100))
self.start_wide = self.df_wide.index[10000]
self.stop_wide = self.df_wide.index[15000]
self.df2 = DataFrame(
{
'float1': np.random.randn(N),
'float2': np.random.randn(N)
},
index=date_range('1/1/2000', periods=N))
self.start = self.df2.index[10000]
self.stop = self.df2.index[15000]
self.df_wide2 = DataFrame(np.random.randn(N, 100),
index=date_range('1/1/2000', periods=N))
self.df_dc = DataFrame(np.random.randn(N, 10),
columns=['C%03d' % i for i in range(10)])
self.fname = '__test__.h5'
self.store = HDFStore(self.fname)
self.store.put('fixed', self.df)
self.store.put('fixed_mixed', self.df_mixed)
self.store.append('table', self.df2)
self.store.append('table_mixed', self.df_mixed)
self.store.append('table_wide', self.df_wide)
self.store.append('table_wide2', self.df_wide2)
def teardown(self):
self.store.close()
self.remove(self.fname)
def time_read_store(self):
self.store.get('fixed')
def time_read_store_mixed(self):
self.store.get('fixed_mixed')
def time_write_store(self):
self.store.put('fixed_write', self.df)
def time_write_store_mixed(self):
self.store.put('fixed_mixed_write', self.df_mixed)
def time_read_store_table_mixed(self):
self.store.select('table_mixed')
def time_write_store_table_mixed(self):
self.store.append('table_mixed_write', self.df_mixed)
def time_read_store_table(self):
self.store.select('table')
def time_write_store_table(self):
self.store.append('table_write', self.df)
def time_read_store_table_wide(self):
self.store.select('table_wide')
def time_write_store_table_wide(self):
self.store.append('table_wide_write', self.df_wide)
def time_write_store_table_dc(self):
self.store.append('table_dc_write', self.df_dc, data_columns=True)
def time_query_store_table_wide(self):
self.store.select('table_wide',
where="index > self.start_wide and "
"index < self.stop_wide")
def time_query_store_table(self):
self.store.select('table',
where="index > self.start and "
"index < self.stop")
def time_store_repr(self):
repr(self.store)
def time_store_str(self):
str(self.store)
def time_store_info(self):
self.store.info()
class HDFStoreDataFrame(BaseIO):
def setup(self):
N = 25000
index = tm.makeStringIndex(N)
self.df = DataFrame(
{"float1": np.random.randn(N), "float2": np.random.randn(N)}, index=index
)
self.df_mixed = DataFrame(
{
"float1": np.random.randn(N),
"float2": np.random.randn(N),
"string1": ["foo"] * N,
"bool1": [True] * N,
"int1": np.random.randint(0, N, size=N),
},
index=index,
)
self.df_wide = DataFrame(np.random.randn(N, 100))
self.start_wide = self.df_wide.index[10000]
self.stop_wide = self.df_wide.index[15000]
self.df2 = DataFrame(
{"float1": np.random.randn(N), "float2": np.random.randn(N)},
index=date_range("1/1/2000", periods=N),
)
self.start = self.df2.index[10000]
self.stop = self.df2.index[15000]
self.df_wide2 = DataFrame(
np.random.randn(N, 100), index=date_range("1/1/2000", periods=N)
)
self.df_dc = DataFrame(
np.random.randn(N, 10), columns=["C%03d" % i for i in range(10)]
)
self.fname = "__test__.h5"
self.store = HDFStore(self.fname)
self.store.put("fixed", self.df)
self.store.put("fixed_mixed", self.df_mixed)
self.store.append("table", self.df2)
self.store.append("table_mixed", self.df_mixed)
self.store.append("table_wide", self.df_wide)
self.store.append("table_wide2", self.df_wide2)
def teardown(self):
self.store.close()
self.remove(self.fname)
def time_read_store(self):
self.store.get("fixed")
def time_read_store_mixed(self):
self.store.get("fixed_mixed")
def time_write_store(self):
self.store.put("fixed_write", self.df)
def time_write_store_mixed(self):
self.store.put("fixed_mixed_write", self.df_mixed)
def time_read_store_table_mixed(self):
self.store.select("table_mixed")
def time_write_store_table_mixed(self):
self.store.append("table_mixed_write", self.df_mixed)
def time_read_store_table(self):
self.store.select("table")
def time_write_store_table(self):
self.store.append("table_write", self.df)
def time_read_store_table_wide(self):
self.store.select("table_wide")
def time_write_store_table_wide(self):
self.store.append("table_wide_write", self.df_wide)
def time_write_store_table_dc(self):
self.store.append("table_dc_write", self.df_dc, data_columns=True)
def time_query_store_table_wide(self):
self.store.select(
"table_wide", where="index > self.start_wide and index < self.stop_wide"
)
def time_query_store_table(self):
self.store.select("table", where="index > self.start and index < self.stop")
def time_store_repr(self):
repr(self.store)
def time_store_str(self):
str(self.store)
def time_store_info(self):
self.store.info()
#store = {} #dictionary to store objects
#hdf = store = {} #dictionary to store objects
am2320 = AM2320(1)
while (1):
hdf = HDFStore(filename)
store1 = []
jj = 12
curr_time = datetime.datetime.now()
while (jj > 0):
jj = jj - 1
(t, h) = am2320.readSensor()
#curr_time = datetime.datetime.now()
#yr = datetime.datetime.strftime(curr_time, "%Y")
#mn = datetime.datetime.strftime(curr_time, "%m")
#dy = datetime.datetime.strftime(curr_time, "%d")
#tm = datetime.datetime.strftime(curr_time, "%H:%m")
#store1.append([yr,mn,dy,tm,t,h])
store1.append([t, h])
sleep(300)
#df = DataFrame(store1,columns=('Year', 'Month', 'Day', 'Time', 'Temp', 'Humidity'))
df = DataFrame(store1,
index=date_range(start=curr_time, periods=12, freq='300S'),
columns=('Temp', 'Humidity'))
hdf.append('Weather1', df, format='table', data_columns=True)
# print hdf['Weather1'].shape
#Loading insee data
projection = HDFStore(
'C:\Users\Utilisateur\Documents\GitHub\ga\src\countries\France\sources\data_fr\proj_pop_insee\proj_pop.h5',
'r')
projection_dataframe = projection[
'/projpop0760_FECbasESPbasMIGbas'] # <-Do not know the precise meaning of this. For testing only
#Combining
concatened = concat([population, projection_dataframe], verify_integrity=True)
concatened = concatened.reset_index()
concatened['year'] = concatened.year.convert_objects(convert_numeric=True)
concatened = concatened.set_index(['age', 'sex', 'year'])
#Saving as HDF5 file
export = HDFStore('neo_population.h5')
export.append('pop', concatened, data_columns=concatened.columns)
export.close()
export = HDFStore('neo_population.h5', 'r')
print export
#Creating the simulation object
net_payments = Simulation()
net_payments.set_population(population)
France = 'France'
net_payments.set_country(France)
r = 0.0
g = 0.01
net_payments.set_discount_rate(r)
net_payments.set_growth_rate(g)
# print net_payments
projection = HDFStore(
"C:\Users\Utilisateur\Documents\GitHub\ga\src\countries\France\sources\data_fr\proj_pop_insee\proj_pop.h5", "r"
)
projection_dataframe = projection[
"/projpop0760_FECbasESPbasMIGbas"
] # <-Do not know the precise meaning of this. For testing only
# Combining
concatened = concat([population, projection_dataframe], verify_integrity=True)
concatened = concatened.reset_index()
concatened["year"] = concatened.year.convert_objects(convert_numeric=True)
concatened = concatened.set_index(["age", "sex", "year"])
# Saving as HDF5 file
export = HDFStore("neo_population.h5")
export.append("pop", concatened, data_columns=concatened.columns)
export.close()
export = HDFStore("neo_population.h5", "r")
print export
# Creating the simulation object
net_payments = Simulation()
net_payments.set_population(population)
France = "France"
net_payments.set_country(France)
r = 0.0
g = 0.01
net_payments.set_discount_rate(r)
net_payments.set_growth_rate(g)
def read_raw_tecplot_folder_and_write_pandas_hdf5(
case_folder,
root = 0,
output_file = 0,
output_root = 0,
overwrite = False,
):
from os.path import isfile,join,splitext
from os import listdir
from progressbar import ProgressBar,Percentage,Bar
from progressbar import ETA,SimpleProgress
from pandas import DataFrame, HDFStore
# File related things ######################################################
if not output_file:
output_file = case_folder+"_Aligned.hdf5"
if not output_root:
output_root = '/media/carlos/6E34D2CD34D29783/' +\
'2015-02_SerrationPIV/TR_Data_Location_Calibrated_Article3'
if not output_file.endswith('_Aligned.hdf5'):
output_file = output_file.replace("_Aligned.hdf5","")+"_Aligned.hdf5"
if 'STE' in case_folder or 'z10' in case_folder:
output_file = output_file.replace( '.hdf5', '_AirfoilNormal.hdf5' )
if isfile(join( output_root, output_file )) and not overwrite:
print " Exiting; file exists:\n {0}".format(output_file)
return 0
else:
print " Writing\n {0}".format(output_file)
# ##########################################################################
time_step_files = sorted(
[join(root,case_folder,f) for f in listdir(join( root, case_folder )) \
if splitext(f)[1] == '.dat']
)
progress = ProgressBar(
widgets=[
Bar(),' ',
Percentage(),' ',
ETA(), ' (file ',
SimpleProgress(),')'],
maxval=len(time_step_files)
).start()
cnt = 0
hdf_store = HDFStore( join( output_root, output_file ) )
for f,t in zip(time_step_files,range(len(time_step_files))):
df_t = read_tecplot_file(
tecplot_folder = join( root, case_folder ),
tecplot_time_step_file = f,
time_step = t,
)
if cnt == 0:
df = df_t.copy()
else:
df = df.append( df_t, ignore_index = True)
if cnt == 50:
df = correct_df_translation_rotation( df )\
[['x','y','t','u','v','w']]
df = df.sort_values( by = ['x','y','t'] )
#df.set_index( ['x','y'], inplace = True)
if t == 0:
hdf_store.put( 'data', df ,
data_columns = ['x','y','t'],
format = 't')
else:
hdf_store.append( 'data', df ,
data_columns = ['x','y','t'],
format = 't')
cnt = 0
df = DataFrame()
cnt += 1
progress.update(t)
progress.finish()
hdf_store.close()
return 1
def store_to_liam(self):
'''
Sauvegarde des données au format utilisé ensuite par le modèle Til
Séléctionne les variables appelée par Til derrière
Appelle des fonctions de Liam2
'''
path_param = os.path.join(path_model, "til_base_model\param", "globals.csv")
path = os.path.join(path_model, self._output_name())
h5file = tables.openFile( path, mode="w")
# 1 - on met d'abord les global en recopiant le code de liam2
# globals_def = {'periodic': {'path': 'param/globals.csv'}}
globals_def = {'periodic': {'path': path_param}}
const_node = h5file.createGroup("/", "globals", "Globals")
localdir = path_model
for global_name, global_def in globals_def.iteritems():
print(" %s" % global_name)
req_fields = ([('PERIOD', int)] if global_name == 'periodic'
else [])
kind, info = imp.load_def(localdir, global_name,
global_def, req_fields)
# comme dans import
# if kind == 'ndarray':
# imp.array_to_disk_array(h5file, const_node, global_name, info,
# title=global_name,
# compression=compression)
# else:
assert kind == 'table'
fields, numlines, datastream, csvfile = info
imp.stream_to_table(h5file, const_node, global_name, fields,
datastream, numlines,
title="%s table" % global_name,
buffersize=10 * 2 ** 20,
compression=None)
# 2 - ensuite on s'occupe des entities
ent_node = h5file.createGroup("/", "entities", "Entities")
for ent_name in ['ind','foy','men','futur','past']:
entity = eval('self.'+ ent_name)
if entity is not None:
entity = entity.fillna(-1)
ent_table = entity.to_records(index=False)
dtypes = ent_table.dtype
final_name = of_name_to_til[ent_name]
table = h5file.createTable(ent_node, final_name, dtypes, title="%s table" % final_name)
table.append(ent_table)
table.flush()
if ent_name == 'men':
entity = entity.loc[entity['id']>-1]
ent_table2 = entity[['pond','id','period']].to_records(index=False)
dtypes2 = ent_table2.dtype
table = h5file.createTable(ent_node, 'companies', dtypes2, title="'companies table")
table.append(ent_table2)
table.flush()
if ent_name == 'ind':
ent_table2 = entity[['agem','sexe','pere','mere','id','findet','period']].to_records(index=False)
dtypes2 = ent_table2.dtype
table = h5file.createTable(ent_node, 'register', dtypes2, title="register table")
table.append(ent_table2)
table.flush()
h5file.close()
# 3 - table longitudinal
# Note: on conserve le format pandas ici
store = HDFStore(path)
for varname, tab in self.longitudinal.iteritems():
#format to liam
table = tab
table['id'] = table.index
store.append('longitudinal/' + varname, table)
store.close()
def rd_hydstra(varto, sites=None, data_source='A', from_date=None, to_date=None, from_mod_date=None, to_mod_date=None, interval='day', qual_codes=[30, 20, 10, 11, 21, 18], concat_data=True, export=None):
"""
Function to read in data from Hydstra's database using HYDLLP. This function extracts all sites with a specific variable code (varto).
Parameters
----------
varto : int or float
The hydstra conversion data variable (140.00 is flow).
sites: list of str
List of sites to be returned. None includes all sites.
data_source : str
Hydstra datasource code (usually 'A').
from_date: str
The starting date for the returned data given other constraints.
to_date: str
The ending date for the returned data given other constraints.
from_mod_date: str
The starting date when the data has been modified.
to_mod_date: str
The ending date when the data has been modified.
interval : str
The frequency of the output data (year, month, day, hour, minute, second, period). If data_type is 'point', then interval cannot be 'period' (use anything else, it doesn't matter).
qual_codes : list of int
The quality codes for output.
export_path: str
Path string where the data should be saved, or None to not save the data.
Return
------
DataFrame
In long format with site and time as a MultiIndex and data, qual_code, and hydstra_var_code as columns.
"""
### Parameters
device_data_type = {100: 'mean', 140: 'mean', 143: 'mean', 450: 'mean', 110: 'mean', 130: 'mean', 10: 'tot'}
today1 = date.today()
dtype_dict = {'Site': 'varchar', 'HydstraCode': 'smallint', 'Time': 'date', 'Value': 'float', 'QualityCode': 'smallint', 'ModDate': 'date'}
### Determine the period lengths for all sites and variables
sites_var_period = hydstra_sites_var_periods(varto=varto, sites=sites, data_source=data_source)
# sites_list = sites_var_period.site.unique().tolist()
varto_list = sites_var_period.varto.unique().astype('int32').tolist()
### Restrict period ranges - optional
if isinstance(from_date, str):
from_date1 = Timestamp(from_date)
from_date_df = sites_var_period.from_date.apply(lambda x: x if x > from_date1 else from_date1)
sites_var_period['from_date'] = from_date_df
if isinstance(to_date, str):
to_date1 = Timestamp(to_date)
to_date_df = sites_var_period.to_date.apply(lambda x: x if x > to_date1 else to_date1)
sites_var_period['to_date'] = to_date_df
### Only pull out data according to the modifcation date ranges - optional
if isinstance(from_mod_date, str):
sites_block = sites_var_period[sites_var_period.varfrom == sites_var_period.varto]
varto_block = sites_block.varto.unique().astype('int32').tolist()
chg1 = hydstra_data_changes(varto_block, sites_block.site.unique(), from_mod_date=from_mod_date, to_mod_date=to_mod_date).drop('to_date', axis=1)
if 140 in varto_list:
sites_flow = sites_var_period[(sites_var_period.varfrom != sites_var_period.varto) & (sites_var_period.varto == 140)]
chg2 = rating_changes(sites_flow.site.unique().tolist(), from_mod_date=from_mod_date, to_mod_date=to_mod_date)
chg1 = concat([chg1, chg2])
chg1.rename(columns={'from_date': 'mod_date'}, inplace=True)
chg3 = merge(sites_var_period, chg1, on=['site', 'varfrom', 'varto'])
chg4 = chg3[chg3.to_date > chg3.mod_date].copy()
chg4['from_date'] = chg4['mod_date']
sites_var_period = chg4.drop('mod_date', axis=1).copy()
### Convert datetime to date as str
sites_var_period2 = sites_var_period.copy()
sites_var_period2['from_date'] = sites_var_period2['from_date'].dt.date.astype(str)
sites_var_period2['to_date'] = sites_var_period2['to_date'].dt.date.astype(str)
site_str_len = sites_var_period2.site.str.len().max()
if isinstance(export, str):
if export.endswith('.h5'):
store = HDFStore(export, mode='a')
data = DataFrame()
for tup in sites_var_period2.itertuples(index=False):
print('Processing site: ' + str(tup.site))
varto = tup.varto
data_type = device_data_type[varto]
df = rd_hydstra_db([tup.site], data_type=data_type, start=tup.from_date, end=tup.to_date, varfrom=tup.varfrom, varto=varto, interval=interval, qual_codes=qual_codes)
if df.empty:
continue
df['HydstraCode'] = varto
if varto == 143:
df.loc[:, 'data'] = df.loc[:, 'data'] * 0.001
df['HydstraCode'] = 140
### Make sure the data types are correct
df.rename(columns={'data': 'Value', 'qual_code': 'QualityCode'}, inplace=True)
df.index.rename(['Site', 'Time'], inplace=True)
df.loc[:, 'QualityCode'] = df['QualityCode'].astype('int32')
df.loc[:, 'HydstraCode'] = df['HydstraCode'].astype('int32')
df.loc[:, 'ModDate'] = today1
if isinstance(export, dict):
df = df.reset_index()
from_date1 = str(df.Time.min().date())
to_date1 = str(df.Time.max().date())
del_rows_dict = {'where_col': {'Site': [str(tup.site)], 'HydstraCode': [str(df['HydstraCode'][0])]}, 'from_date':from_date1, 'to_date': to_date1, 'date_col': 'Time'}
write_sql(df, dtype_dict=dtype_dict, del_rows_dict=del_rows_dict, drop_table=False, create_table=False, **export)
elif isinstance(export, str):
if export.endswith('.h5'):
try:
store.append(key='var_' + str(varto), value=df, min_itemsize={'site': site_str_len})
except Exception as err:
store.close()
raise err
if concat_data:
data = concat([data, df])
if isinstance(export, str):
store.close()
if concat_data:
return data
def extract_relevant_data( case_list = [], exceptions = [], y_delta_locs = [],
x_2h_locs = [] , plot = False):
""" This will extract the wall normal data at the spanwise location
TE at a certain y density
"""
from os import listdir
from os.path import join,split
from pandas import DataFrame, HDFStore, read_pickle
from boundary_layer_routines import return_bl_parameters
from raw_data_processing_routines import decript_case_name
from progressbar import ProgressBar,Percentage
from progressbar import Bar,ETA,SimpleProgress
from numpy import array, round, linspace
from data_cleaning_routines import show_surface_from_df
x_2h_locs = round( array( x_2h_locs ), 2 )
y_delta_locs = round( array( y_delta_locs ), 2 )
# Get the available HDF5 files #############################################
hdf5_root = '/media/carlos/6E34D2CD34D29783/' +\
'2015-02_SerrationPIV/TR_Data_Location_Calibrated_Article3'
if not len(case_list):
hdf5_files = [f for f in listdir( hdf5_root ) \
if f.endswith('.hdf5') \
and not f in exceptions ]
else:
hdf5_files = [f for f in listdir( hdf5_root ) \
if f.endswith('.hdf5') \
and f in case_list ]
# ##########################################################################
for hf in [join( hdf5_root, f ) for f in hdf5_files]:
f = split( hf )[1].replace('_AirfoilNormal','')\
.replace('_Aligned.hdf5','')
print " Extracting data from {0}".format(f)
print " at the normalized streamwise locations:"
print " {0}".format( x_2h_locs )
hdf_t = HDFStore( hf, 'r' )
# Get the available coordinates ########################################
hf_coords = hdf_t.select('data', where = [ 't = 0' ],
columns = [ 'x', 'y' ] )
# ######################################################################
# Turn the non-dim requested locations into physical coords ############
requested_locations = []
requested_normalized_locations = []
#for x,x_norm in zip(x_2h_locs * tooth_length, x_2h_locs):
# for y_d in y_delta_locs:
# bl_params = return_bl_parameters( f , [x] )
# d_99 = bl_params.delta_99.values[0]
# #if "STE" in f:
# # d_99 = 9.4
# y = y_d * d_99
# requested_locations.append( (x,y) )
# requested_normalized_locations.append( ( x_norm, y_d ) )
# Get the normalization locations depending on the case ################
if 'z00' in f and not 'STE' in f:
x_bl_loc = 40
elif 'z05' in f:
x_bl_loc = 20
elif 'z10' in f or 'STE' in f:
x_bl_loc = 0
bl_params = return_bl_parameters( f , [x_bl_loc] )
d_99 = bl_params.delta_99.values[0]
for x,x_norm in zip(x_2h_locs * tooth_length, x_2h_locs):
for y_d in y_delta_locs:
y = y_d * d_99
requested_locations.append( (x,y) )
requested_normalized_locations.append( ( x_norm, y_d ) )
print " Normalizing to a BL thickness of {0:.2f} mm".\
format(d_99)
# ######################################################################
available_xy_locs = hf_coords[
( hf_coords.x > min( x_2h_locs ) * 40. ) & \
( hf_coords.x < max( x_2h_locs ) * 40. ) & \
( hf_coords.y > min( y_delta_locs ) * d_99 ) & \
( hf_coords.y < max( y_delta_locs ) * d_99 )
][ ['x','y'] ]
available_xy_locs = [tuple(x) for x in available_xy_locs.values]
if plot:
trailing_edge,phi,alpha,U,z = decript_case_name( f )
if trailing_edge == 'serrated': device = 'Sr20R21'
elif trailing_edge == 'straight': device = 'STE'
elif trailing_edge == 'slitted': device = 'Slit20R21'
case_name = "{0}_phi{1}_alpha{2}_U{3}_loc{4}_tr.dat".format(
device, phi, alpha, U, z
)
df_av = read_pickle( 'averaged_data/' + case_name + '.p' )
show_surface_from_df( df_av , points = available_xy_locs ,
plot_name = 'ReservedData/' + f + '.png'
)
query = ''
cnt_all = 0
cnt = 0
time_series_hdf = HDFStore( 'ReservedData/' + f + '.hdf5' , 'w' )
vertical_split_blocks = 10
progress = ProgressBar(
widgets=[
Bar(),' ',
Percentage(),' ',
ETA(), ' (query bunch ',
SimpleProgress(),')'],
maxval = vertical_split_blocks
).start()
# Don't try to get it all at once; split the vertical in 4 pieces
y_ranges = linspace(
min( y_delta_locs ),
max( y_delta_locs ),
vertical_split_blocks
) * d_99
xmin = min(x_2h_locs) * 40.
xmax = max(x_2h_locs) * 40.
for ymin, ymax in zip( y_ranges[:-1], y_ranges[1:] ):
query = " x>={0} & x<{1} & y>={2} & y<{3} ".\
format( xmin, xmax, ymin, ymax )
df_t = hdf_t.select(
key = 'data',
where = [ query ],
)
df_t['near_x_2h'] = round( df_t.x / 40., 4 )
df_t['near_y_delta'] = round( df_t.y / d_99, 4 )
if not cnt:
time_series_hdf.put( 'data', df_t ,
data_columns = [
'near_x_2h',
'near_y_delta',
't'
],
format = 't')
else:
time_series_hdf.append( 'data', df_t ,
data_columns = [
'near_x_2h',
'near_y_delta',
't'
],
format = 't')
cnt_all += 1
cnt += 1
progress.update(cnt_all)
df_t = DataFrame()
progress.finish()
hdf_t.close()
time_series_hdf.close()
def append_hdfs(self, df, path, key):
try:
store = HDFStore(path)
store.append(key, df)
except:
print("Error for appending data to {0} in {1}".format(key, path))
def junk():
population = read_csv('C:\Users\Utilisateur\Documents\GitHub\ga\src\countries\France\sources\data_fr\pop.csv', sep=',')
# print population.columns
population = population.set_index(['age', 'sex'])
population = population.stack()
population = population.reset_index()
population['level_2'] = population.level_2.convert_objects(convert_numeric=True)
population['year'] = population['level_2']
population['pop'] = population[0]
del population['level_2']
del population[0]
population = population.set_index(['age', 'sex', 'year'])
#Remove the years 2007 and beyond to ensure integrity when combined with INSEE data
year = list(range(1991, 2007, 1))
filter_year = array([x in year for x in population.index.get_level_values(2)])
population = population.iloc[filter_year, :]
#Loading insee data
projection = HDFStore('C:\Users\Utilisateur\Documents\GitHub\ga\src\countries\France\sources\data_fr\proj_pop_insee\proj_pop.h5', 'r')
projection_dataframe = projection['/projpop0760_FECbasESPbasMIGbas'] # <-Do not know the precise meaning of this. For testing only
#Combining
concatened = concat([population, projection_dataframe], verify_integrity = True)
concatened = concatened.reset_index()
concatened['year'] = concatened.year.convert_objects(convert_numeric=True)
concatened = concatened.set_index(['age', 'sex', 'year'])
#Saving as HDF5 file
export = HDFStore('neo_population.h5')
export.append('pop', concatened, data_columns = concatened.columns)
export.close()
export = HDFStore('neo_population.h5', 'r')
print export
#Creating the simulation object
net_payments = Simulation()
net_payments.set_population(population)
France = 'France'
net_payments.set_country(France)
r = 0.0
g = 0.01
net_payments.set_discount_rate(r)
net_payments.set_growth_rate(g)
# print net_payments
# print net_payments.growth_rate, net_payments.discount_rate, net_payments.country
net_payments.load_population("neo_population.h5", 'pop')
net_payments.load_profiles("C:\Users\Utilisateur\Documents\GitHub\ga\src\countries\profiles.h5", "profiles.h5")
year_length = 100
net_payments.set_population_projection(year_length = year_length, method = "exp_growth", rate = 0.02)
net_payments.set_tax_projection(method = "per_capita", typ = None, rate = g, discount_rate = r)
net_payments.create_cohorts()
#Creating a column with total taxes paid.
for typ in net_payments._types:
net_payments['total'] += hstack(net_payments[typ])
print net_payments['total']
def junk():
population = read_csv(
'C:\Users\Utilisateur\Documents\GitHub\ga\src\countries\France\sources\data_fr\pop.csv',
sep=',')
# print population.columns
population = population.set_index(['age', 'sex'])
population = population.stack()
population = population.reset_index()
population['level_2'] = population.level_2.convert_objects(
convert_numeric=True)
population['year'] = population['level_2']
population['pop'] = population[0]
del population['level_2']
del population[0]
population = population.set_index(['age', 'sex', 'year'])
#Remove the years 2007 and beyond to ensure integrity when combined with INSEE data
year = list(range(1991, 2007, 1))
filter_year = array(
[x in year for x in population.index.get_level_values(2)])
population = population.iloc[filter_year, :]
#Loading insee data
projection = HDFStore(
'C:\Users\Utilisateur\Documents\GitHub\ga\src\countries\France\sources\data_fr\proj_pop_insee\proj_pop.h5',
'r')
projection_dataframe = projection[
'/projpop0760_FECbasESPbasMIGbas'] # <-Do not know the precise meaning of this. For testing only
#Combining
concatened = concat([population, projection_dataframe],
verify_integrity=True)
concatened = concatened.reset_index()
concatened['year'] = concatened.year.convert_objects(convert_numeric=True)
concatened = concatened.set_index(['age', 'sex', 'year'])
#Saving as HDF5 file
export = HDFStore('neo_population.h5')
export.append('pop', concatened, data_columns=concatened.columns)
export.close()
export = HDFStore('neo_population.h5', 'r')
print export
#Creating the simulation object
net_payments = Simulation()
net_payments.set_population(population)
France = 'France'
net_payments.set_country(France)
r = 0.0
g = 0.01
net_payments.set_discount_rate(r)
net_payments.set_growth_rate(g)
# print net_payments
# print net_payments.growth_rate, net_payments.discount_rate, net_payments.country
net_payments.load_population("neo_population.h5", 'pop')
net_payments.load_profiles(
"C:\Users\Utilisateur\Documents\GitHub\ga\src\countries\profiles.h5",
"profiles.h5")
year_length = 100
net_payments.set_population_projection(year_length=year_length,
method="exp_growth",
rate=0.02)
net_payments.set_tax_projection(method="per_capita",
typ=None,
rate=g,
discount_rate=r)
net_payments.create_cohorts()
#Creating a column with total taxes paid.
for typ in net_payments._types:
net_payments['total'] += hstack(net_payments[typ])
print net_payments['total']
import numpy as np
from pandas import HDFStore, DataFrame
# create (or open) an hdf5 file and opens in append mode
hdf = HDFStore('data/hdata.h5')
df = DataFrame(np.random.rand(1000, 3), columns=('A', 'B', 'C'))
# put the dataset in the storage
hdf.put('d1', df, format='table', data_columns=True)
print(hdf['d1'].shape)
hdf.append('d1',
DataFrame(np.random.rand(5, 3), columns=('A', 'B', 'C')),
format='table',
data_columns=True)
df = DataFrame(np.random.rand(1000, 3), columns=('A', 'B', 'C'))
# put the dataset in the storage
hdf.put('d2', df, format='table', data_columns=True)
print(hdf['d2'].shape)
hdf.append('d2',
DataFrame(np.random.rand(5, 3), columns=('A', 'B', 'C')),
format='table',
data_columns=True)
hdf.close() # closes the file