def createManagementCompanyData(request):
logger.info("Creating management company Data")
dataloader = DataLoader(request.cls.dataFile, env)
dataloader.deleteManagementAndPropertySetup()
dataloader.createManagementAndProperty()
request.cls.testdata = dataloader.getData()
from datetime import datetime
from utils.DataLoader import DataLoader
from validation.GridSearch import GridSearch
if __name__ == '__main__':
start = datetime.now()
print("Imported modules", flush=True)
dataLoader = DataLoader("dataset4")
print("data loaded", flush=True)
healthy = dataLoader.getData(["healthy"], ["THCA", "LUAD"])
sick = dataLoader.getData(["sick"], ["THCA", "LUAD"])
data = dataLoader.getData(["sick", "healthy"], ["THCA", "LUAD"])
grid_search = GridSearch(sick, healthy, data)
print("got combined data", flush=True)
table = grid_search.get_table_all_at_once()
print("table creation done", flush=True)
grid_search.save_table_to_disk(table, "grid_search_all_at_once_big")
print("saved table to file", flush=True)
table = grid_search.get_table_one_vs_rest()
print("table creation done", flush=True)
grid_search.save_table_to_disk(table, "grid_search_one_vs_rest_big")
print("Imported modules")
dataLoader = DataLoader("dataset5")
dimReducer = DimensionalityReducer()
analyzer = Analyzer()
clusVal = ClusterValidator()
classVal = ClassificationValidator()
sampler = Sampler()
print("data loaded")
#healthy = dataLoader.getData(["healthy"], ["THCA","LUAD"])
#healthy = sampler.over_sample(healthy)
start = datetime.now()
sick = dataLoader.getData(["sick"], ["all"])
healthy = dataLoader.getData(["healthy"], ["all"])
gene_labels = dataLoader.getGeneLabels()
print("got combined data")
print(datetime.now() - start)
selected_genes = dimReducer.getOneAgainstRestFeatures(
sick, healthy, 10, "norm", "exclude")
"""
#selected_genes = dimReducer.getFeatures(data, 10)
#selected_genes = dimReducer.getOneAgainstRestFeatures(data, "",5)
#selected_genes = dimReducer.getNormalizedFeatures(sick, healthy, k=10)
#selected_genes = dimReducer.getOneAgainstRestFeatures(sick, healthy, 10, "norm", "relief")
#selected_genes = dimReducer.getOneAgainstRestFeatures(sick, healthy, 10, "norm", "exclude")
from utils.plot import plotScatter
from utils import Expressions
from validation.Analyzer import Analyzer
print("Imported modules")
dataLoader = DataLoader("dataset4")
dimReducer = DimensionalityReducer()
analyzer = Analyzer()
print("data loaded")
#%%
healthy = dataLoader.getData(["healthy"], ["THCA", "SARC", "LUAD", "GBM"])
#sick = dataLoader.getData(["sick"], ["THCA","GBM"])
gene_labels = dataLoader.getGeneLabels()
print("got combined data")
# %%
selected_genes = dimReducer.getFeatures(healthy)
print("Unsampled")
plotScatter(healthy, selected_genes, gene_labels)
# %%
sampler = Sampler()
print("Standard Sampling")
sampled = sampler.over_sample(healthy, change_labels=True)
plotScatter(sampled, selected_genes, gene_labels)