Newer
Older
from juliacall import Main as jl
import numpy as np
import pandas as pd
class LWPLSR:
"""The lwpls regression model from Jchemo (M. Lesnoff)
Returns:
self.scores (DataFrame): various metrics and scores
self.predicted_results (Dictionary): Dict containing all predicted results (train, test, cross-validation)
self.mod (Julia model): the prepared model
"""
"""Initiate the LWPLSR and prepare data for Julia computing."""
if action == 'Model_Creation':
# get train / test data from dataset
self.x_train, self.y_train, self.x_test, self.y_test = [dataset[i] for i in range(4)]
# calculate number of KFolds and get CV data from dataset
self.nb_fold = int((len(dataset)-4)/4)
for i in range(self.nb_fold):
setattr(self, "xtr_fold"+str(i+1), dataset[i+7])
setattr(self, "ytr_fold"+str(i+1), dataset[i+13])
setattr(self, "xte_fold"+str(i+1), dataset[i+4])
setattr(jl, "xtr_fold"+str(i+1), dataset[i+7])
setattr(jl, "ytr_fold"+str(i+1), dataset[i+13])
setattr(jl, "xte_fold"+str(i+1), dataset[i+4])
# prepare to send dataframes to julia and Jchemo (with the jl. prefix)
jl.x_train, jl.y_train, jl.x_test, jl.y_test = self.x_train, self.y_train, self.x_test, self.y_test
# Get parameters for preTreatment of the spectra (acquired from a global PLSR)
self.preT = preT
# initialize vars from the class
y_shape = self.y_test.shape
self.pred_test = np.zeros(shape=(y_shape[0], 1))
self.pred_train = np.zeros(shape=(y_shape[0], 1))
self.mod = ""
self.best_lwplsr_params = np.zeros(shape=(5, 1))
self.predicted_results = {}
elif action == 'Prediction':
self.x_spectra, self.y, self.x_pred = [dataset[i] for i in range(3)]
# prepare to send dataframes to julia and Jchemo (with the jl. prefix)
jl.x_spectra, jl.y, jl.x_pred = self.x_spectra, self.y, self.x_pred
BARTHES Nicolas
committed
self.preT = preT
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
def Jchemo_lwplsr_fit(self):
"""Send data to Julia to fit lwplsr.
Args:
self.x_train (DataFrame):
self.y_train (DataFrame):
self.x_test (DataFrame):
self.y_test (DataFrame):
Returns:
self.mod (Julia model): the prepared model
"""
# launch Julia Jchemo lwplsr and convert DataFrames from Python Pandas DataFrame to Julia DataFrame
jl.seval("""
using DataFrames
using Pandas
using Jchemo
x_train |> Pandas.DataFrame |> DataFrames.DataFrame
y_train |> Pandas.DataFrame |> DataFrames.DataFrame
x_test |> Pandas.DataFrame |> DataFrames.DataFrame
y_test |> Pandas.DataFrame |> DataFrames.DataFrame
""")
# apply pre-treatments on X data
print('LWPLSR - preTreatment')
# apply pre-treatments to X data before working with
jl.npoint = self.preT['window_length']
jl.deriv = self.preT['deriv']
jl.degree = self.preT['polyorder']
if self.preT['polyorder'] > 0:
jl.seval("""
mod1 = model(snv; centr = true, scal = true)
mod2 = model(savgol; npoint = npoint, deriv = deriv, degree = degree)
""")
if self.preT['normalization'] == "No_transformation":
jl.seval("""
preMod = mod2
""")
elif self.preT['normalization'] == 'Snv':
jl.seval("""
preMod = pip(mod1, mod2)
""")
jl.seval("""
fit!(preMod, x_train)
x_train = transf(preMod, x_train)
x_test = transf(preMod, x_test)
""")
# LWPLSR tuning
print('LWPLSR - tuning')
# set tuning parameters to test
jl.seval("""
nlvdis = [5; 10; 15] ; metric = [:eucl; :mah]
h = [1; 2; 6; Inf] ; k = [30; 80; 200]
nlv = 5:15
pars = Jchemo.mpar(nlvdis = nlvdis, metric = metric, h = h, k = k)
""")
# split Train data into Cal/Val for tuning
jl.seval("""
pct = .3
ntrain = Jchemo.nro(x_train)
nval = Int(round(pct * ntrain))
s = Jchemo.samprand(ntrain, nval)
Xcal = x_train[s.train, :]
ycal = y_train[s.train]
Xval = x_train[s.test, :]
yval = y_train[s.test]
ncal = ntrain - nval
""")
# Create LWPLSR model and tune with GridScore
jl.seval("""
mod = Jchemo.model(Jchemo.lwplsr)
res = gridscore(mod, Xcal, ycal, Xval, yval; score = Jchemo.rmsep, pars, nlv, verbose = false)
u = findall(res.y1 .== minimum(res.y1))[1] #best parameters combination
""")
# save best lwplsr parameters
self.best_lwplsr_params = {'nlvdis' : jl.res.nlvdis[jl.u], 'metric' : str(jl.res.metric[jl.u]), 'h' : jl.res.h[jl.u], 'k' : jl.res.k[jl.u], 'nlv' : jl.res.nlv[jl.u]}
print('best lwplsr params ' + str(self.best_lwplsr_params))
# run LWPLSR model with best parameters
jl.seval("""
mod = Jchemo.model(Jchemo.lwplsr; nlvdis = res.nlvdis[u], metric = res.metric[u], h = res.h[u], k = res.k[u], nlv = res.nlv[u])
# Fit model
Jchemo.fit!(mod, x_train, y_train)
""")
# save Julia Jchemo model
self.mod = jl.mod
def Jchemo_lwplsr_predict_fit(self):
"""Send data to Julia to fit lwplsr.
Args:
self.x_spectra (DataFrame):
self.y (DataFrame):
self.x_pred (DataFrame):
Returns:
self.mod (Julia model): the prepared model
"""
# launch Julia Jchemo lwplsr and convert DataFrames from Python Pandas DataFrame to Julia DataFrame
jl.seval("""
using DataFrames
using Pandas
using Jchemo
x_spectra |> Pandas.DataFrame |> DataFrames.DataFrame
y |> Pandas.DataFrame |> DataFrames.DataFrame
x_pred |> Pandas.DataFrame |> DataFrames.DataFrame
""")
# LWPLSR tuning
BARTHES Nicolas
committed
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
print('LWPLSR - no tuning, using best parameters from model creation')
# # set tuning parameters to test
# jl.seval("""
# nlvdis = [5; 10; 15] ; metric = [:eucl; :mah]
# h = [1; 2; 6; Inf] ; k = [30; 80; 200]
# nlv = 5:15
# pars = Jchemo.mpar(nlvdis = nlvdis, metric = metric, h = h, k = k)
# """)
# # split Train data into Cal/Val for tuning
# jl.seval("""
# pct = .3
# ntrain = Jchemo.nro(x_spectra)
# nval = Int(round(pct * ntrain))
# s = Jchemo.samprand(ntrain, nval)
# Xcal = x_spectra[s.train, :]
# ycal = y[s.train]
# Xval = x_spectra[s.test, :]
# yval = y[s.test]
# ncal = ntrain - nval
# """)
#
# # Create LWPLSR model and tune with GridScore
# jl.seval("""
# mod = Jchemo.model(Jchemo.lwplsr)
# # res = gridscore(mod, Xcal, ycal, Xval, yval; score = Jchemo.rmsep, pars, nlv, verbose = false)
# # u = findall(res.y1 .== minimum(res.y1))[1] #best parameters combination
# # """)
# # save best lwplsr parameters
# self.best_lwplsr_params = {'nlvdis' : jl.res.nlvdis[jl.u], 'metric' : str(jl.res.metric[jl.u]), 'h' : jl.res.h[jl.u], 'k' : jl.res.k[jl.u], 'nlv' : jl.res.nlv[jl.u]}
# print('best lwplsr params ' + str(self.best_lwplsr_params))
# import best params from model creation
jl.nlvdis = self.preT['nlvdis']
jl.metric = self.preT['metric']
jl.h = self.preT['h']
jl.k = self.preT['k']
jl.nlv = self.preT['nlv']
# run LWPLSR model with best parameters
jl.seval("""
BARTHES Nicolas
committed
mod = Jchemo.model(Jchemo.lwplsr; nlvdis = nlvdis, metric = Symbol(metric), h = h, k = k, nlv = nlv)
# Fit model
Jchemo.fit!(mod, x_spectra, y)
""")
# save Julia Jchemo model
self.mod = jl.mod
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
def Jchemo_lwplsr_predict(self):
"""Send data to Julia to predict with lwplsr.
Args:
self.mod (Julia model): the prepared model
self.x_train (DataFrame):
self.y_train (DataFrame):
self.x_test (DataFrame):
self.y_test (DataFrame):
Returns:
self.pred_test (Julia DataFrame): predicted values on x_test
self.pred_train (Julia DataFrame): predicted values on x_train
"""
# Predictions on x_test and store in self.pred
self.pred_test = jl.seval("""
println("LWPLSR - start test predict")
res = Jchemo.predict(mod, x_test)
res.pred
""")
self.pred_train = jl.seval("""
println("LWPLSR - start train predict")
res = Jchemo.predict(mod, x_train)
res.pred
""")
print('LWPLSR - end')
def Jchemo_lwplsr_predict_predict(self):
"""Send data to Julia to predict with lwplsr.
Args:
self.mod (Julia model): the prepared model
self.x_spectra (DataFrame):
self.y (DataFrame):
self.x_pred (DataFrame):
Returns:
self.y_pred (Julia DataFrame): predicted values on x_pred
"""
# Predictions on x_test and store in self.pred
self.y_pred = jl.seval("""
println("LWPLSR - start y predict")
res = Jchemo.predict(mod, x_pred)
res.pred
""")
print('LWPLSR - end')
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
def Jchemo_lwplsr_cv(self):
"""Send Cross-Validation data to Julia to fit & predict with lwplsr.
Args:
self.best_lwplsr_params: the best parameters to use (from tuning) for CV
self.xtr_fold1 (DataFrame):
self.ytr_fold1 (DataFrame):
self.xte_fold1 (DataFrame):
Returns:
self.pred_cv (Julia DataFrame): predicted values on x_train with Cross-Validation
"""
for i in range(self.nb_fold):
jl.Xtr = getattr(self, "xtr_fold"+str(i+1))
jl.Ytr = getattr(self, "ytr_fold"+str(i+1))
jl.Xte = getattr(self, "xte_fold"+str(i+1))
# convert Python Pandas DataFrame to Julia DataFrame
jl.seval("""
using DataFrames
using Pandas
using Jchemo
Xtr |> Pandas.DataFrame |> DataFrames.DataFrame
Ytr |> Pandas.DataFrame |> DataFrames.DataFrame
Xte |> Pandas.DataFrame |> DataFrames.DataFrame
""")
# set lwplsr parameters as the best one from tuning
jl.nlvdis = int(self.best_lwplsr_params['nlvdis'])
jl.metric = self.best_lwplsr_params['metric']
jl.h = self.best_lwplsr_params['h']
jl.k = int(self.best_lwplsr_params['k'])
jl.nlv = int(self.best_lwplsr_params['nlv'])
jl.seval("""
println("LWPLSR - start CV mod")
mod_cv = Jchemo.model(Jchemo.lwplsr; nlvdis = nlvdis, metric = Symbol(metric), h = h, k = k, nlv = nlv)
# Fit model
Jchemo.fit!(mod_cv, Xtr, Ytr)
""")
pred_cv = jl.seval("""
println("LWPLSR - start CV predict")
res = Jchemo.predict(mod_cv, Xte)
res.pred
""")
# save predicted values for each KFold in the predicted_results dictionary
@property
def pred_data_(self):
# convert predicted data from x_test to Pandas DataFrame
self.predicted_results["pred_data_train"] = DataFrame(self.pred_train)
self.predicted_results["pred_data_test"] = DataFrame(self.pred_test)
@property
def predict_pred_data_(self):
# convert predicted data from x_test to Pandas DataFrame
self.predicted_results["y_pred"] = DataFrame(self.y_pred)
return self.predicted_results