def main(filename, numberOfComponents):
df = utilities.readDataFile(filename)
df = utilities.getDataWithTimeIndex(df)
df = df.dropna()
subdir = filename.split('/')[-2]
columns, relevantColumns, labelNames, columnUnits, timestamps = getConfig(
subdir)
if relevantColumns is not None:
df = utilities.dropIrrelevantColumns(df, [relevantColumns, labelNames])
prints.printEmptyLine()
pca = analysis.pca(df, numberOfComponents, relevantColumns, labelNames)
prints.printExplainedVarianceRatio(pca)
def main(filename):
df = utilities.readDataFile(filename)
df = utilities.getDataWithTimeIndex(df)
df = df.dropna()
subdir = filename.split('/')[-2]
columns, relevantColumns, labelNames, columnUnits, timestamps = getConfig(
subdir)
if relevantColumns is not None:
df = utilities.dropIrrelevantColumns(df, [relevantColumns, labelNames])
prints.printEmptyLine()
covMat = analysis.correlationMatrix(df)
prints.printCorrelationMatrix(covMat, df, labelNames)
def dropIrrelevantColumns(df, args):
relevantColumns, columnDescriptions = args
print("Columns before removal: ")
prints.printColumns(df, columnDescriptions)
dfcolumns = df.columns
for column in dfcolumns:
if column not in relevantColumns:
df = df.drop(column, axis=1)
prints.printEmptyLine()
print("Columns after removal: ")
prints.printColumns(df, columnDescriptions)
prints.printEmptyLine()
return df
df_iris = pd.read_csv(filename).drop(column, axis=1)
print("Writing file {}".format(target_file))
df_iris.to_csv(target_file, index=False)
pyName = "dropColumn.py"
arguments = [
"- filename (string)",
"- target filename (string)",
"- name of column (string)",
]
# usage: python dropColumn.py file targetfile column
if __name__ == "__main__":
start_time = time.time()
prints.printEmptyLine()
print("Running", pyName)
print("Prints dataframe")
prints.printEmptyLine()
try:
filename = sys.argv[1]
target_file = sys.argv[2]
column = sys.argv[3]
except IndexError:
print(pyName, "was called with inappropriate arguments")
print("Please provide the following arguments:")
for argument in arguments:
print(argument)
sys.exit()
def getDataByTimeframe(df, start, end):
print("Finding data between", start, "and", end)
df = df.loc[start:end]
print("Found " + str(df.shape[0]) + " rows")
prints.printEmptyLine()
return df