clementpoiret

import ants
import click
import numpy as np
from rich.console import Console
from rich.table import Table

CLASS_LABELS = ["Dentate Gyrus", "CA1", "CA2", "CA3", "Subiculum"]


@click.command()

clementpoiret

# Maintainer: Clément POIRET <poiret dot clement at outlook dot fr>

_pkgname="hyprland"
pkgname="${_pkgname}-displaylink-git"
pkgver="0.38.1"
pkgrel=1
pkgdesc="A dynamic tiling Wayland compositor based on wlroots that doesn't sacrifice on its looks. (DisplayLink patch)"
arch=(any)
url="https://github.com/hyprwm/Hyprland"
license=('BSD')

clementpoiret

import time

import pandas as pd
import numpy as np
import pingouin as pg
from scipy.stats import pearsonr


def mse(y, y_hat):
    """Let's define a dummy error term :)"""

clementpoiret

import torch
import pymia.evaluation.evaluator as eval_
import pymia.evaluation.metric as metric

y = torch.randint(0, 4, (1, 16, 16, 16))
y_hat = y * .8 - 1

metrics = [
    metric.DiceCoefficient(),
    metric.VolumeSimilarity(),

clementpoiret

clementpoiret

# Prediction
observation = np.array(1).reshape(-1,1)
y_pred = model.predict(observation)
y_truth = gradient * observation + w0

print("Prediction : {}\nTruth : {}".format(y_pred, y_truth))

clementpoiret

# Showing data, alongside prediction
x = np.linspace(0, 2, 10).reshape(-1, 1)
y_truth = gradient * x + w0
y_estimated = model.coef_ * x + model.intercept_

plt.scatter(X_train, y_train, label="Data")
plt.plot(x, y_truth, label="Truth")
plt.plot(x, y_estimated, label="Model")
plt.legend();

clementpoiret

# Model's Definition and Training
model = LinearRegression(fit_intercept = True)
model.fit(X_train, y_train)

# Creating test sets
X_test = 2 * np.random.random_sample((10, 1))
y_test = gradient * X_test + w0 + 0.1 * np.random.random_sample((10, 1))

# Score
r2 = model.score(X_test, y_test)

clementpoiret

# Model's Definition and Training
model = LinearRegression(fit_intercept = True)
model.fit(X_train, y_train)

# Creating test sets
X_test = 2 * np.random.random_sample((10, 1))
y_test = gradient * X_test + w0 + 0.1 * np.random.random_sample((10, 1))

# Score
r2 = model.score(X_test, y_test)

clementpoiret

# Real Parameters
gradient = 0.5
w0 = 1

# Data synthesis
X_train = 2 * np.random.random_sample((20, 1))
y_train = gradient * X_train + w0 + 0.1 * np.random.random_sample((20, 1))

# Plot
plt.scatter(X_train, y_train);