def test_column_info(self):
s = r"#COLUMNINFO= 1, m, Sondeerlengte, 1"
v = utils.parse_column_info(s, 1, MAP_QUANTITY_NUMBER_COLUMN_NAME_CPT)
self.assertEqual(v, "penetration_length")
h = {"COLUMNINFO": [["1", "m", "Sondeerlengte", "1"]]}
v = utils.parse_column_info(h, 1, MAP_QUANTITY_NUMBER_COLUMN_NAME_CPT)
self.assertEqual(v, "penetration_length")
def parse_data_column_info(header_s,
data_s,
sep,
columns_number,
columns_info=None):
if columns_info is None:
col = list(
map(
lambda x: utils.parse_column_info(
header_s, x, MAP_QUANTITY_NUMBER_COLUMN_NAME_BORE),
range(1, columns_number + 1),
))
return pd.read_csv(io.StringIO(data_s),
sep=sep,
names=col,
index_col=False,
usecols=col)
else:
return pd.read_csv(
io.StringIO(data_s),
sep=sep,
names=columns_info,
index_col=False,
usecols=columns_info,
)
def parse_data_column_info(headers,
data_s,
sep,
columns_number,
columns_info=None):
if columns_info is None:
col = list(
map(
lambda x: utils.parse_column_info(
headers, x, MAP_QUANTITY_NUMBER_COLUMN_NAME_BORE),
range(1, columns_number + 1),
))
return pl.read_csv(
io.StringIO(data_s),
sep=sep,
new_columns=col,
has_headers=False,
projection=list(range(0, len(col))),
)
else:
return pl.read_csv(
io.StringIO(data_s),
sep=sep,
new_columns=columns_info,
has_headers=False,
)
def determine_column_names(headers, columns_number=None, columns_info=None):
if columns_number is None and columns_info is None:
columns_number = utils.parse_columns_number(headers)
if columns_number is not None:
columns_info = []
for column_number in range(1, columns_number + 1):
columns_info.append(
utils.parse_column_info(
headers, column_number,
MAP_QUANTITY_NUMBER_COLUMN_NAME_CPT))
return columns_info
def parse_data(header_s, data_s, columns_number=None, columns_info=None):
df = {}
if columns_number is None and columns_info is None:
columns_number = utils.parse_columns_number(header_s)
if columns_number is not None:
columns_info = []
for column_number in range(1, columns_number + 1):
column_info = utils.parse_column_info(
header_s, column_number,
MAP_QUANTITY_NUMBER_COLUMN_NAME_CPT)
columns_info.append(column_info)
df = pd.read_csv(io.StringIO(data_s.replace('!', '')),
sep=r';|\s+|,|\|\s*',
names=columns_info,
index_col=False,
engine='python')
return df
def parse_data_column_info(header_s,
data_s,
sep,
columns_number,
columns_info=None):
if columns_info is None:
columns_info = []
for column_number in range(1, columns_number + 1):
column_info = utils.parse_column_info(
header_s, column_number,
MAP_QUANTITY_NUMBER_COLUMN_NAME_BORE)
columns_info.append(column_info)
df_column_info = pd.read_csv(io.StringIO(data_s),
sep=sep,
names=columns_info,
index_col=False,
usecols=columns_info)
return df_column_info
def parse_data(header_s, data_s, columns_number=None, columns_info=None):
if columns_number is None and columns_info is None:
columns_number = utils.parse_columns_number(header_s)
if columns_number is not None:
columns_info = []
for column_number in range(1, columns_number + 1):
column_info = utils.parse_column_info(
header_s, column_number, MAP_QUANTITY_NUMBER_COLUMN_NAME_CPT
)
columns_info.append(column_info)
new_data = data_s.replace("!", "")
separator = utils.find_separator(header_s)
return pd.read_csv(
io.StringIO(new_data),
sep=separator,
names=columns_info,
index_col=False,
engine="python",
)
def test_column_info(self):
s = r'#COLUMNINFO= 1, m, Sondeerlengte, 1'
v = utils.parse_column_info(s, 1, MAP_QUANTITY_NUMBER_COLUMN_NAME_CPT)
self.assertEqual(v, "penetration_length")