Pyinstaller cannot compile project with sklearn - python-3.x

Question

I'm trying to compile this simple python 3 (pyconda) machine learning project with sklearn and these imports (it's a simple Ridge regression predictor):
from datetime import date
import pandas as pd
import numpy as np
from sklearn.linear_model import Ridge
pd.options.mode.chained_assignment = None
class covidUpdater:
situazione = ""
def getCovidUpdate(self):
url = "https://raw.githubusercontent.com/pcm-dpc/COVID-19/master/dati-andamento-nazionale/dpc-covid19-ita-andamento-nazionale.csv"
ds = pd.read_csv(url)
return ds.tail(self.giorni)
def __init__(self):
pass
def setGiorni(self,giorni):
self.giorni = giorni
self.situazione = self.getCovidUpdate()
def getCampo(self,campo):
return self.situazione[[campo]]
def getMaxLength(self):
ur1l = "https://raw.githubusercontent.com/pcm-dpc/COVID-19/master/dati-andamento-nazionale/dpc-covid19-ita-andamento-nazionale.csv"
ds1 = pd.read_csv(ur1l)
return len(ds1)
def formatTable(self,campo):
giorniPrediction = 1
updater = covidUpdater()
updater.setGiorni(self.giorni)
updaterFuture = covidUpdater()
updaterFuture.setGiorni(self.giorni+giorniPrediction)
datiCampo = updater.getCampo(campo)
datiCampoFuture = updaterFuture.getCampo(campo)
campo_domani = str(campo) + "_domani"
datiCampo[campo_domani] = datiCampoFuture.shift(-giorniPrediction)
datiCampo = datiCampo.head(self.giorni-giorniPrediction)
datiCampo["id"] = range(datiCampo.iloc[:, 0].size)
return datiCampo
def main():
campo = "nuovi_positivi"
updater = covidUpdater()
giorni = int(input("Inserisci numero giorni da usare come dataset> ") or updater.getMaxLength())
updater.setGiorni(giorni)
print("Giorni selezionati: ",giorni)
df = updater.formatTable(campo)
print("Imposto l'algoritmo di predizione")
X = df.iloc[:, 0].values.reshape(-1,1)
Y = df.iloc[:, 1].values.reshape(-1,1)
regr = Ridge(alpha=1.0,normalize=False,tol=0.1,solver="lsqr")
print("Avvio l'algoritmo di predizione")
regr.fit(X,Y)
Y_pred = regr.predict(X)
print("-----------------------------------\n")
print("Giorni in esame: "+ str(giorni)+"\n")
print("Predizione di (" + str(date.today()) + ") : "+ str(regr.predict(np.array([Y[Y.size-1]])))+"\n")
print("fattore R2: "+ str(regr.score(Y,Y_pred))+"\n")
print("-----------------------------------"+"\n")
if __name__ == "__main__":
main()
By using this command:
pyinstaller --noconfirm --onedir --console --hidden-import "sklearn.linear_model.Ridge" "PATH"
I have this log the final error is:
Traceback
Traceback (most recent call last):
File "d:\pyconda\lib\site-packages\auto_py_to_exe\packaging.py", line 131, in package
run_pyinstaller()
File "d:\pyconda\lib\site-packages\PyInstaller\__main__.py", line 114, in run
run_build(pyi_config, spec_file, **vars(args))
File "d:\pyconda\lib\site-packages\PyInstaller\__main__.py", line 65, in run_build
PyInstaller.building.build_main.main(pyi_config, spec_file, **kwargs)
File "d:\pyconda\lib\site-packages\PyInstaller\building\build_main.py", line 720, in main
build(specfile, kw.get('distpath'), kw.get('workpath'), kw.get('clean_build'))
File "d:\pyconda\lib\site-packages\PyInstaller\building\build_main.py", line 667, in build
exec(code, spec_namespace)
File "C:\Users\Alex\AppData\Local\Temp\tmp854ytoyk\covid2.spec", line 17, in <module>
noarchive=False)
File "d:\pyconda\lib\site-packages\PyInstaller\building\build_main.py", line 242, in __init__
self.__postinit__()
File "d:\pyconda\lib\site-packages\PyInstaller\building\datastruct.py", line 160, in __postinit__
self.assemble()
File "d:\pyconda\lib\site-packages\PyInstaller\building\build_main.py", line 419, in assemble
self.graph.process_post_graph_hooks()
File "d:\pyconda\lib\site-packages\PyInstaller\depend\analysis.py", line 365, in process_post_graph_hooks
module_hook.post_graph()
File "d:\pyconda\lib\site-packages\PyInstaller\depend\imphook.py", line 440, in post_graph
self._load_hook_module()
File "d:\pyconda\lib\site-packages\PyInstaller\depend\imphook.py", line 407, in _load_hook_module
self.hook_module_name, self.hook_filename)
File "d:\pyconda\lib\site-packages\PyInstaller\compat.py", line 588, in importlib_load_source
return mod_loader.load_module()
File "<frozen importlib._bootstrap_external>", line 407, in _check_name_wrapper
File "<frozen importlib._bootstrap_external>", line 907, in load_module
File "<frozen importlib._bootstrap_external>", line 732, in load_module
File "<frozen importlib._bootstrap>", line 265, in _load_module_shim
File "<frozen importlib._bootstrap>", line 696, in _load
File "<frozen importlib._bootstrap>", line 677, in _load_unlocked
File "<frozen importlib._bootstrap_external>", line 728, in exec_module
File "<frozen importlib._bootstrap>", line 219, in _call_with_frames_removed
File "d:\pyconda\lib\site-packages\_pyinstaller_hooks_contrib\hooks\stdhooks\hook-zmq.py", line 21, in <module>
hiddenimports = ['zmq.utils.garbage'] + collect_submodules('zmq.backend')
File "d:\pyconda\lib\site-packages\PyInstaller\utils\hooks\__init__.py", line 595, in collect_submodules
repr(pkg_dir), package))
File "d:\pyconda\lib\site-packages\PyInstaller\utils\hooks\__init__.py", line 79, in exec_statement
return __exec_python_cmd(cmd)
File "d:\pyconda\lib\site-packages\PyInstaller\utils\hooks\__init__.py", line 68, in __exec_python_cmd
txt = exec_python(*cmd, env=pp_env)
File "d:\pyconda\lib\site-packages\PyInstaller\compat.py", line 521, in exec_python
return exec_command(*cmdargs, **kwargs)
File "d:\pyconda\lib\site-packages\PyInstaller\compat.py", line 316, in exec_command
out = out.decode(encoding)
UnicodeDecodeError: 'utf-8' codec can't decode byte 0x8a in position 112: invalid start byte
Full log here: https://pastebin.com/XuBeLz3X

Answer 1

I think you should start with the first error in the log:
3560572 INFO: Analyzing hidden import 'sklearn.linear_model.Ridge'
3560576 ERROR: Hidden import 'sklearn.linear_model.Ridge' not found
Have you had a look at this thread with the Hidden import error? How do you resolve 'hidden imports not found!' warnings in pyinstaller for scipy?
I think you need to adjust your hidden imports, so that 'sklearn.linear_model.Ridge' can be found.
And I just tried running your code in Google Colab (https://colab.research.google.com/) and it works there. Perhaps you can run your code there?