def read_file_to_gpmap(
input_file_name,
wildtype=None,
):
"""Read the input file for GPSeer.
This should be a CSV file with the following columns:
genotypes, phenotypes, n_replicates, stdeviations
"""
df = pd.read_csv(input_file_name)
required_columns = ["genotypes", "phenotypes"]
optional_columns = ["stdeviations", "n_replicates"]
for c in required_columns:
try:
df[c]
except AttributeError:
err = "input file ({}) must contain a column labeled '{}'".format(
input_file_name, c)
return AttributeError(err)
# If wildtype is not given, use the first genotype in the input file.
if not wildtype:
wildtype = df.loc[0, 'genotypes']
# Fill in missing columns for the GenotypePhenotypeMap
for col in optional_columns:
if col not in df.columns:
df[col] = None
gpm = GenotypePhenotypeMap.read_dataframe(df, wildtype)
return gpm
def fit_transform(self, X=None, y=None, **kwargs):
self.fit(X=X, y=y, **kwargs)
ypred = self.predict(X=X)
# Transform map.
gpm = GenotypePhenotypeMap.read_dataframe(
dataframe=self.gpm.data[ypred==1],
wildtype=self.gpm.wildtype,
mutations=self.gpm.mutations
)
return gpm
def fit_transform(self, X=None, y=None, **kwargs):
self.fit(X=X, y=y, **kwargs)
linear_phenotypes = self.transform(X=X, y=y)
# Transform map.
gpm = GenotypePhenotypeMap.read_dataframe(
dataframe=self.gpm.data,
wildtype=self.gpm.wildtype,
mutations=self.gpm.mutations
)
gpm.data['phenotypes'] = linear_phenotypes
return gpm
def split_gpm(gpm, idx=None, nobs=None, fraction=None):
"""Split GenotypePhenotypeMap into two sets, a training and a test set.
Parameters
----------
data : pandas.DataFrame
full dataset to split.
idx : list
List of indices to include in training set
nobs : int
number of observations in training.
fraction : float
fraction in training set.
Returns
-------
train_gpm : GenotypePhenotypeMap
training set.
test_gpm : GenotypePhenotypeMap
test set.
"""
train, test = split_data(gpm.data, idx=idx, nobs=nobs, fraction=fraction)
train_gpm = GenotypePhenotypeMap.read_dataframe(train,
wildtype=gpm.wildtype,
mutations=gpm.mutations)
test_gpm = GenotypePhenotypeMap.read_dataframe(test,
wildtype=gpm.wildtype,
mutations=gpm.mutations)
return train_gpm, test_gpm
