lmassaron

https://xgboost.readthedocs.io/en/latest/tutorials/model.html
https://towardsdatascience.com/entropy-how-decision-trees-make-decisions-2946b9c18c8
https://github.com/Microsoft/LightGBM/issues/2062#issuecomment-477120125
https://papers.nips.cc/paper/6907-lightgbm-a-highly-efficient-gradient-boosting-decision-tree.pdf
https://explained.ai/gradient-boosting/
https://www.youtube.com/watch?v=5CWwwtEM2TA

lmassaron

https://uk.mathworks.com/help/vision/ug/faster-r-cnn-basics.html
https://medium.com/@jonathan_hui/map-mean-average-precision-for-object-detection-45c121a31173
https://medium.com/@14prakash/the-intuition-behind-retinanet-eb636755607d
https://cv-tricks.com/object-detection/faster-r-cnn-yolo-ssd/
https://towardsdatascience.com/retinanet-how-focal-loss-fixes-single-shot-detection-cb320e3bb0de
https://medium.com/data-from-the-trenches/object-detection-with-deep-learning-on-aerial-imagery-2465078db8a9

https://medium.com/deep-learning-journals/fast-scnn-explained-and-implemented-using-tensorflow-2-0-6bd17c17a49e

https://github.com/Dharun/Tensorflow-License-Plate-Detection/blob/master/numplate_recognition_detection.py

lmassaron

def add_noise(series, noise_level):
    return series * (1 + noise_level * np.random.randn(len(series)))

def target_encode(trn_series=None, tst_series=None, target=None, k=1, f=1, noise_level=0):
    """
    Encoding is computed like in the following paper by:
	
    Micci-Barreca, Daniele. "A preprocessing scheme for high-cardinality categorical attributes in classification and prediction problems." ACM SIGKDD Explorations Newsletter 3.1 (2001): 27-32.
    
    trn_series (pd.Series) : categorical feature in-sample

lmassaron

from keras import layers
from keras import models
import tensorflow as tf


#
# generator input params
#

rand_dim = (1, 1, 2048)  # dimension of the generator's input tensor (gaussian noise)

lmassaron

class AllMyFields:
    def __init__(self, dictionary):
        for k, v in dictionary.items():
            setattr(self, k, v)
 
o = AllMyFields({'alpha': 1, 'beta': 2})

o.a

lmassaron

# Derived from the original script https://www.kaggle.com/gemartin/load-data-reduce-memory-usage 
# by Guillaume Martin

def reduce_mem_usage(df, verbose=True):
    numerics = ['int16', 'int32', 'int64', 'float16', 'float32', 'float64']
    start_mem = df.memory_usage().sum() / 1024**2    
    for col in df.columns:
        col_type = df[col].dtypes
        if col_type in numerics:
            c_min = df[col].min()

lmassaron

from sklearn.base import BaseEstimator, TransformerMixin
from sklearn.ensemble import RandomForestClassifier, ExtraTreesClassifier

class ClassifierTransformer(BaseEstimator, TransformerMixin):
    """
    Classifier's estimates of a regression problem using oof
    """
    def __init__(self, estimator=None, n_classes=2, cv=3):
        self.estimator = estimator
        self.n_classes = n_classes

lmassaron

def poly1_cross_entropy(logits, labels, epsilon=1.0):
    # pt, CE, and Poly1 have shape [batch].
    pt = tf.reduce_sum(labels * tf.nn.softmax(logits), axis=-1)
    CE = tf.nn.softmax_cross_entropy_with_logits(labels, logits)
    Poly1 = CE + epsilon * (1 - pt)
    return Poly1
    
def poly1_focal_loss(logits, labels, epsilon=1.0, gamma=2.0):
    # p, pt, FL, and Poly1 have shape [batch, num of classes].
    p = tf.math.sigmoid(logits)

lmassaron

from scipy.stats import beta, norm
import numpy as np

data = np.array([0.0, 0.0, 0.1, 0.1, 0.2, 0.4, 0.5, 0.7, 0.8, 0.8, 0.9, 1.0, 1.0, 1.0])
eps = 0.000001

data[data==0.0] += eps
data[data==1.0] -= eps

a, b, loc, scale = beta.fit(data, floc=0, fscale=1)

lmassaron

dealing with zeros and ones in a beta regression
------------------------------------------------
Smithson, M. & Verkuilen, J. 
A better lemon squeezer? Maximum-likelihood regression with beta-distributed dependent variables. 
Psychol. Methods 11, 54–71 (2006). 
DOI: 10.1037/1082-989X.11.1.54

https://stats.stackexchange.com/questions/31300/dealing-with-0-1-values-in-a-beta-regression

zero-one inflated beta regression