def CCM(pathIn="./",
dataFile="",
dataFrame=None,
pathOut="./",
predictFile="",
E=0,
Tp=0,
knn=0,
tau=1,
columns="",
target="",
libSizes="",
sample=0,
random=True,
replacement=False,
seed=0,
verbose=False,
showPlot=False):
'''Convergent Cross Mapping on path/file.'''
# Establish DF as empty list or Pandas DataFrame for CCM()
if dataFile:
DF = pyBindEDM.DF()
elif isinstance(dataFrame, DataFrame):
if dataFrame.empty:
raise Exception("CCM(): dataFrame is empty.")
DF = pyEDM.AuxFunc.PandasDataFrametoDF(dataFrame)
else:
raise Exception("CCM(): Invalid data input.")
# D is a Python dict from pybind11 < cppEDM CCM
D = pyBindEDM.CCM(pathIn, dataFile, DF, pathOut, predictFile, E, Tp, knn,
tau, columns, target, libSizes, sample, random,
replacement, seed, verbose)
df = DataFrame(D) # Convert to pandas DataFrame
if showPlot:
title = dataFile + "\nE=" + str(E)
ax = df.plot('LibSize', [df.columns[1], df.columns[2]],
title=title,
linewidth=3)
ax.set(xlabel="Library Size", ylabel="Correlation ρ")
axhline(y=0, linewidth=1)
show()
return df
def CCM( pathIn = "./",
dataFile = "",
dataFrame = None,
pathOut = "./",
predictFile = "",
E = 0,
Tp = 0,
knn = 0,
tau = -1,
exclusionRadius = 0,
columns = "",
target = "",
libSizes = "",
sample = 0,
random = True,
replacement = False,
seed = 0,
embedded = False,
includeData = False,
parameterList = False,
verbose = False,
showPlot = False ) :
'''Convergent Cross Mapping on path/file.'''
# Establish DF as empty list or Pandas DataFrame for CCM()
if dataFile :
DF = pyBindEDM.DF()
elif isinstance( dataFrame, DataFrame ) :
if dataFrame.empty :
raise Exception( "CCM(): dataFrame is empty." )
DF = pyEDM.AuxFunc.PandasDataFrametoDF( dataFrame )
else :
raise Exception( "CCM(): Invalid data input." )
# If columns, libSizes, target are not string, but iterable, convert to string
if pyEDM.AuxFunc.NotStringIterable( columns ) :
columns = ' '.join( map( str, columns ) )
if pyEDM.AuxFunc.NotStringIterable( libSizes ) :
libSizes = ' '.join( map( str, libSizes ) )
if pyEDM.AuxFunc.NotStringIterable( target ) :
target = ' '.join( map( str, target ) )
# D is a Python dict from pybind11 < cppEDM CCM
D = pyBindEDM.CCM( pathIn,
dataFile,
DF,
pathOut,
predictFile,
E,
Tp,
knn,
tau,
exclusionRadius,
columns,
target,
libSizes,
sample,
random,
replacement,
seed,
embedded,
includeData,
parameterList,
verbose )
# D has { "LibMeans" : DF }
# and if includeData has : { PredictStats1 : DF, PredictStats2 : DF }
libMeans = DataFrame( D[ "LibMeans" ] ) # Convert to pandas DataFrame
# If includeData, create dict with means and individual prediction stats
if includeData :
CM = { 'LibMeans' : libMeans,
'PredictStats1' : DataFrame( D[ "PredictStats1" ] ),
'PredictStats2' : DataFrame( D[ "PredictStats2" ] ) }
if parameterList and includeData :
CM[ 'parameters' ] = D[ 'parameters' ]
if showPlot :
title = dataFile + "\nE=" + str(E)
ax = libMeans.plot( 'LibSize',
[ libMeans.columns[1], libMeans.columns[2] ],
title = title, linewidth = 3 )
ax.set( xlabel = "Library Size", ylabel = "Correlation ρ" )
axhline( y = 0, linewidth = 1 )
show()
if includeData :
return CM
else :
return libMeans