print ('Correlation with {column_name}'.format(column_name = column_name))
print (corr_matrix[column_name].sort_values(ascending=False))
def save_fig(fig_id, tight_layout=True):
'''
save figue to folder. file name will include current timestamp
'''
fig_id += '_' + str(time.time())
path = os.path.join('.', "images", fig_id + ".png")
print("Saving figure", fig_id)
if tight_layout:
plt.tight_layout()
plt.savefig(path, format='png', dpi=300)
if __name__ == '__main__':
housing = load_data(HOUSING_PATH, 'housing.csv')
print (housing.head())
print (housing.describe())
scatter_plot_by_column(housing, 'longitude', 'latitude', 'population', 'median_house_value')
attributes = ["median_house_value", "median_income", "total_rooms", "housing_median_age"]
scatter_matrix_for_attributes(housing, attributes)
#example for feature mapping - better correlation with the target value
housing["rooms_per_household"] = housing["total_rooms"]/housing["households"]
housing["bedrooms_per_room"] = housing["total_bedrooms"]/housing["total_rooms"]
housing["population_per_household"] = housing["population"]/housing["households"]
#see correlation
show_correlation_with_column(housing, 'median_house_value')
def unsupervised(Arguments):
'''
Pairwise MOCA calculations that are executed if the Phenotype argument is False (the default). Similar to
so-called 'supervised' pairwise mode, except that no performance metrics are calculated (sens, spec, PPV, NPV, etc.).
In unspervised mode, you can compare all inter-datatype pairs for two datatypes, or all intra-datatype pairs for
a single datatype.
'''
if len(Arguments.Data) > 2:
print "Unsupervised pairwise calculations can consider no more that two datatypes at a time."
print "If you provide only one datatype, all intra-datatype pairs will be considered. If you"
print "provide two datatypes, all inter-datatype comparisons will be made. Please change the"
print "'Data = ' field. Exiting..."
exit()
Data = load_data(Arguments)
Features = list(chain(*Data.Transformed.Features.values()))
Variates = list(chain(*Data.Transformed.Variates.values()))
if len(Arguments.Data) == 1:
Features1 = Features
Features2 = Features
if len(Arguments.Data) == 2:
Features1 = Data.Transformed.Features[Arguments.Data[0]]
Features2 = Data.Transformed.Features[Arguments.Data[1]]
PValues = {}
Interactions = {}
SampleCounts = {}
CaseCounts = {} #just the positive class here
Performances = {}
EffectSizes = {}
Tested = []
for Feature1 in Features1:
Tested.append(Feature1)
for Feature2 in Features2:
if Feature2 not in Tested:
a,b,c,d = contingency_table(Variates[Features.index(Feature1)], Variates[Features.index(Feature2)],
NA=Arguments.NA)
PValue = fisher(a,b,c,d)
PValues[tuple([Feature1, Feature2])] = PValue.two_tail
Interactions[tuple([Feature1, Feature2])] = interaction(PValue)
SampleCounts[tuple([Feature1, Feature2])] = a + b + c + d
CaseCounts[tuple([Feature1, Feature2])] = a + c
#A placeholder solely to make pairwise post-processing generalizable
Performances[tuple([Feature1, Feature2])] = "NA"
EffectSizes[tuple([Feature1, Feature2])] = "NA"
FDRs = p_adjust(PValues, Arguments.CorrectionMethod)
for Pair, PValue in PValues.items():
if FDRs[PValue] < Arguments.FDR:
pass
else:
PValues.pop(Pair, None)
Interactions.pop(Pair, None)
SampleCounts.pop(Pair, None)
CaseCounts.pop(Pair, None)
Performances.pop(Pair, None)
EffectSizes.pop(Pair, None)
Results = {}
Results["Report"] = make_report(Data.Labels, PValues.keys(), Arguments)
Results["PValues"] = PValues
Results["Interactions"] = Interactions
Results["FDRs"] = FDRs
Results["SampleCounts"] = SampleCounts
Results["CaseCounts"] = CaseCounts
Results["Performances"] = Performances
Results["EffectSizes"] = EffectSizes
if Arguments.Filename.lower() == "default":
Pickle = "_".join(["Pairwise", "_".join(sorted(Arguments.Data)), str(Arguments.FeatureMin),
Arguments.CorrectionMethod])
else:
Pickle = Arguments.Filename
cPickle.dump(Results, open(get_path("MOCA.results") + "/" + Pickle, "wb"), -1)
return
def pairwise_continuous(Arguments):
'''
'''
if len(Arguments.Data) > 2:
print "Unsupervised pairwise calculations can consider no more that two datatypes at a time."
print "If you provide only one datatype, all intra-datatype pairs will be considered. If you"
print "provide two datatypes, all inter-datatype comparisons will be made. Please change the"
print "'Data = ' field. Exiting..."
exit()
Data = load_data(Arguments)
Features = list(chain(*Data.Features.values()))
Variates = list(chain(*Data.Variates.values()))
if Arguments.Phenotype:
Features1 = [Feature for Feature in Features if Arguments.Phenotype in Feature]
Features2 = [Feature for Feature in Features if Arguments.Phenotype not in Feature]
else:
if len(Arguments.Data) == 1:
Features1 = Features
Features2 = Features
if len(Arguments.Data) == 2:
Features1 = Data.Features[Arguments.Data[0]]
Features2 = Data.Features[Arguments.Data[1]]
PValues = {}
Correlations = {}
Tested = []
for Feature1 in Features1:
Tested.append(Feature1)
for Feature2 in Features2:
if Feature2 not in Tested:
PValues[tuple([Feature1, Feature2])] = correlation_pvalue(Variates[Features.index(Feature1)],
Variates[Features.index(Feature2)])
Correlations[tuple([Feature1, Feature2])] = correlation(Variates[Features.index(Feature1)],
Variates[Features.index(Feature2)])
FDRs = p_adjust(PValues, Arguments.CorrectionMethod)
for Pair, PValue in PValues.items():
if FDRs[PValue] < Arguments.FDR:
pass
else:
PValues.pop(Pair, None)
Correlations.pop(Pair, None)
if len(PValues.keys()):
Results = {}
Results["Report"] = make_report(Data.Labels, PValues.keys(), Arguments, Supervised=Arguments.Phenotype)
Results["PValues"] = PValues
Results["Correlations"] = Correlations
Results["FDRs"] = FDRs
if Arguments.Filename.lower() == "default":
Pickle = "_".join(["_".join(sorted(Arguments.Data)), Arguments.CorrectionMethod])
else:
Pickle = Arguments.Filename
cPickle.dump(Results, open(get_path("MOCA.results") + "/" + Pickle, "wb"), -1)
return
def unsupervised(Arguments):
"""
Pairwise MOCA calculations that are executed if the Phenotype argument is False (the default). Similar to
so-called 'supervised' pairwise mode, except that no performance metrics are calculated (sens, spec, PPV, NPV, etc.).
In unspervised mode, you can compare all inter-datatype pairs for two datatypes, or all intra-datatype pairs for
a single datatype.
"""
if len(Arguments.Data) > 2:
print "Unsupervised pairwise calculations can consider no more that two datatypes at a time."
print "If you provide only one datatype, all intra-datatype pairs will be considered. If you"
print "provide two datatypes, all inter-datatype comparisons will be made. Please change the"
print "'Data = ' field. Exiting..."
exit()
Data = load_data(Arguments)
Features = list(chain(*Data.Transformed.Features.values()))
Variates = list(chain(*Data.Transformed.Variates.values()))
if len(Arguments.Data) == 1:
Features1 = Features
Features2 = Features
if len(Arguments.Data) == 2:
Features1 = Data.Transformed.Features[Arguments.Data[0]]
Features2 = Data.Transformed.Features[Arguments.Data[1]]
PValues = {}
Interactions = {}
SampleCounts = {}
CaseCounts = {} # just the positive class here
Performances = {}
EffectSizes = {}
Tested = []
for Feature1 in Features1:
Tested.append(Feature1)
for Feature2 in Features2:
if Feature2 not in Tested:
a, b, c, d = contingency_table(
Variates[Features.index(Feature1)], Variates[Features.index(Feature2)], NA=Arguments.NA
)
PValue = fisher(a, b, c, d)
PValues[tuple([Feature1, Feature2])] = PValue.two_tail
Interactions[tuple([Feature1, Feature2])] = interaction(PValue)
SampleCounts[tuple([Feature1, Feature2])] = a + b + c + d
CaseCounts[tuple([Feature1, Feature2])] = a + c
# A placeholder solely to make pairwise post-processing generalizable
Performances[tuple([Feature1, Feature2])] = "NA"
EffectSizes[tuple([Feature1, Feature2])] = "NA"
FDRs = p_adjust(PValues, Arguments.CorrectionMethod)
for Pair, PValue in PValues.items():
if FDRs[PValue] < Arguments.FDR:
pass
else:
PValues.pop(Pair, None)
Interactions.pop(Pair, None)
SampleCounts.pop(Pair, None)
CaseCounts.pop(Pair, None)
Performances.pop(Pair, None)
EffectSizes.pop(Pair, None)
Results = {}
Results["Report"] = make_report(Data.Labels, PValues.keys(), Arguments)
Results["PValues"] = PValues
Results["Interactions"] = Interactions
Results["FDRs"] = FDRs
Results["SampleCounts"] = SampleCounts
Results["CaseCounts"] = CaseCounts
Results["Performances"] = Performances
Results["EffectSizes"] = EffectSizes
if Arguments.Filename.lower() == "default":
Pickle = "_".join(
["Pairwise", "_".join(sorted(Arguments.Data)), str(Arguments.FeatureMin), Arguments.CorrectionMethod]
)
else:
Pickle = Arguments.Filename
cPickle.dump(Results, open(get_path("MOCA.results") + "/" + Pickle, "wb"), -1)
return
def pairwise_continuous(Arguments):
"""
"""
if len(Arguments.Data) > 2:
print "Unsupervised pairwise calculations can consider no more that two datatypes at a time."
print "If you provide only one datatype, all intra-datatype pairs will be considered. If you"
print "provide two datatypes, all inter-datatype comparisons will be made. Please change the"
print "'Data = ' field. Exiting..."
exit()
Data = load_data(Arguments)
Features = list(chain(*Data.Features.values()))
Variates = list(chain(*Data.Variates.values()))
if Arguments.Phenotype:
Features1 = [Feature for Feature in Features if Arguments.Phenotype in Feature]
Features2 = [Feature for Feature in Features if Arguments.Phenotype not in Feature]
else:
if len(Arguments.Data) == 1:
Features1 = Features
Features2 = Features
if len(Arguments.Data) == 2:
Features1 = Data.Features[Arguments.Data[0]]
Features2 = Data.Features[Arguments.Data[1]]
PValues = {}
Correlations = {}
Tested = []
for Feature1 in Features1:
Tested.append(Feature1)
for Feature2 in Features2:
if Feature2 not in Tested:
PValues[tuple([Feature1, Feature2])] = correlation_pvalue(
Variates[Features.index(Feature1)], Variates[Features.index(Feature2)]
)
Correlations[tuple([Feature1, Feature2])] = correlation(
Variates[Features.index(Feature1)], Variates[Features.index(Feature2)]
)
FDRs = p_adjust(PValues, Arguments.CorrectionMethod)
for Pair, PValue in PValues.items():
if FDRs[PValue] < Arguments.FDR:
pass
else:
PValues.pop(Pair, None)
Correlations.pop(Pair, None)
if len(PValues.keys()):
Results = {}
Results["Report"] = make_report(Data.Labels, PValues.keys(), Arguments, Supervised=Arguments.Phenotype)
Results["PValues"] = PValues
Results["Correlations"] = Correlations
Results["FDRs"] = FDRs
if Arguments.Filename.lower() == "default":
Pickle = "_".join(["_".join(sorted(Arguments.Data)), Arguments.CorrectionMethod])
else:
Pickle = Arguments.Filename
cPickle.dump(Results, open(get_path("MOCA.results") + "/" + Pickle, "wb"), -1)
return
true_positive += 1
else:
false_positive += 1
elif y[i] == 0:
if prediction == 0:
true_negative += 1
else:
false_negative += 1
precision = true_positive / (true_positive + false_positive)
recall = true_positive / (true_positive + false_negative)
return (2 * precision * recall) / (precision + recall)
data = load_data()
train_X = [d[:24] for d in data[:int(len(data) * .8)]]
train_y = [d[24] for d in data[:int(len(data) * .8)]]
test_X = [d[:24] for d in data[int(len(data) * 0.2):]]
test_y = [d[24] for d in data[int(len(data) * 0.2):]]
clf = SVC(kernel='linear')
clf.fit(train_X, train_y)
print("SVC linear training set f-measure: ", f_measure(clf, train_X, train_y))
print("SVC linear test set f-measure: ", f_measure(clf, test_X, test_y))
clf = SVC(kernel='rbf')
clf.fit(train_X, train_y)