Micky774

import numpy as np
from scipy import sparse as sp

def generate_data(n_samples, n_features, n_classes=2, X_density=1, y_sparse=False, dtype=np.float64, random_state=None):
    rng = np.random.RandomState(random_state)
    if X_density < 1:
        X = sp.random(n_samples, n_features, format="csr", density=X_density, random_state=rng)
    else:
        X = np.round(rng.rand(n_samples,n_features)*50).astype(dtype)
    y = np.round(rng.randint(n_classes,size=(n_samples,))).astype(dtype)

Micky774

import numpy as np
from functools import partial
from time import perf_counter
from statistics import mean, stdev
from itertools import product
import csv
from pathlib import Path
from sklearn.neighbors import KNeighborsClassifier

results_path = 'local_artifacts/benchmarks/pwd_labels/predict_proba/large_wide/'

Micky774

# Compile with annotated view to compare generated instructions
# and presence of `__pyx_vtabstruct_*` 
from cython cimport final

# Typedef function pointer
ctypedef int (*f_type)(A)

# Ancestor, serves as interface/ABC
cdef class A:
    cdef f_type func

Micky774

import numpy as np
import scipy.sparse as sp

def generate_data(n_samples, n_features, n_classes=2, X_density=1, y_sparse=False, dtype=np.float64, random_state=None):
    rng = np.random.RandomState(random_state)
    if X_density < 1:
        X = sp.random(n_samples, n_features, format="csr", density=X_density, random_state=rng)
    else:
        X = np.round(rng.rand(n_samples,n_features)*50).astype(dtype)
    y = np.round(rng.randint(n_classes,size=(n_samples,))).astype(dtype)

Micky774

import numpy as np
import scipy.sparse as sp

def generate_data(n_samples, n_features, n_classes=2, X_density=1, y_sparse=False, dtype=np.float64, random_state=None):
    rng = np.random.RandomState(random_state)
    if X_density < 1:
        X = sp.random(n_samples, n_features, format="csr", density=X_density, random_state=rng)
    else:
        X = np.round(rng.rand(n_samples,n_features)*50).astype(dtype)
    y = np.round(rng.randint(n_classes,size=(n_samples,))).astype(dtype)

Micky774

# %%
import numpy as np
import scipy.sparse as sp

def generate_data(n_samples, n_features, n_classes=2, X_density=1, y_sparse=False, dtype=np.float64, random_state=None):
    rng = np.random.RandomState(random_state)
    if X_density < 1:
        X = sp.random(n_samples, n_features, format="csr", density=X_density, random_state=rng)
    else:
        X = np.round(rng.rand(n_samples,n_features)*50).astype(dtype)

Micky774

# %%
from functools import partial
from time import perf_counter
from statistics import mean, stdev
from itertools import product
import csv
from sklearn.neighbors import KNeighborsClassifier
import numpy as np

def make_data(n_samples, n_features, n_classes, n_outs, random_state=None):

Micky774

import numpy as np
import pandas as pd
from sklearn.compose import ColumnTransformer
from sklearn.datasets import fetch_openml
from sklearn.linear_model import LogisticRegression
from sklearn.pipeline import make_pipeline
from sklearn.preprocessing import OneHotEncoder, FunctionTransformer, StandardScaler, KBinsDiscretizer
from sklearn.model_selection import train_test_split
import joblib

Micky774

# %%
import numpy as np
import scipy.sparse as sp

def generate_data(n_samples, n_features, X_density=1, y_sparse=False, dtype=np.float64, random_state=None):
    rng = np.random.RandomState(random_state)
    if X_density < 1:
        X = sp.random(n_samples, n_features, format="csr", density=X_density, random_state=rng)
    else:
        X = np.round(rng.rand(n_samples,n_features)*50).astype(dtype)

Micky774

# %%
import numpy as np
import pandas as pd
from sklearn.compose import ColumnTransformer
from sklearn.datasets import fetch_openml
from sklearn.impute import SimpleImputer
from sklearn.linear_model import LogisticRegression
from sklearn.pipeline import make_pipeline
from sklearn.preprocessing import OneHotEncoder
from sklearn.preprocessing import StandardScaler