conormm

import pandas as pd
import numpy as np
from sklearn.ensemble import RandomForestRegressor
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn.datasets import load_boston
sns.set_style("whitegrid")

X, y = load_boston(return_X_y=True)

conormm

(tidy_docs
 .groupby("doc_id")
 .apply(lambda x: x.assign(
     prev_token = lambda x: x.token.shift(1), 
     next_token = lambda x: x.token.shift(-1))
       )
 .reset_index(drop=True)
 .query("tag == 'POS'")
 .loc[:, ["doc_id", "prev_token", "token", "next_token"]]
)

conormm

def tidy_tokens(docs):
    """Extract tokens and metadata from list of spaCy docs."""
    
    cols = [
        "doc_id", "token", "token_order", "lemma", 
        "ent_type", "tag", "dep", "pos", "is_stop", 
        "is_alpha", "is_digit", "is_punct"
    ]
    
    meta_df = []

conormm

def extract_tokens_plus_meta(doc:spacy.tokens.doc.Doc):
    """Extract tokens and metadata from individual spaCy doc."""
    return [
        (i.text, i.i, i.lemma_, i.ent_type_, i.tag_, 
         i.dep_, i.pos_, i.is_stop, i.is_alpha, 
         i.is_digit, i.is_punct) for i in doc
    ]

conormm

def calcualte_exceedance_probability(exceed_values, posterior):
    n = posterior.shape[1]
    ix = []
    probs_m = []
    probs_05 = []
    probs_95 = []
    for i in exceed_values:
        p = ((posterior>i).sum(1)/n)
        p05 = np.quantile(p, 0.01)
        p95 = np.quantile(p, 0.99)

conormm

ev_model = pm.Model()
with ev_model:
    
    loc = pm.Normal("loc", 5, 10)
    scale = pm.HalfCauchy("scale", 1)
    lik = pm.Gumbel("lik", loc, scale, observed=block_maxima_month.wind_speed)
    ev_trace = pm.sample()
        
norm_model = pm.Model()
with norm_model:

conormm

from sklearn.base import BaseEstimator, ClassifierMixin, RegressorMixin

class CustomClassifier(BaseEstimator, ClassifierMixin):

    def __init__(self):
        pass

    def fit(self, X, y=None):
        pass
    

conormm

from sklearn.base import BaseEstimator, ClassifierMixin
from sklearn.ensemble import GradientBoostingClassifier
from sklearn.linear_model import LogisticRegression
from sklearn.preprocessing import OneHotEncoder

class TreeEmbeddingLogisticRegression(BaseEstimator, ClassifierMixin):
    """Fits a logistic regression model on tree embeddings.
    """
    def __init__(self, **kwargs):
        self.kwargs = kwargs

conormm

from scipy.optimize import curve_fit
from sklearn.base import BaseEstimator, RegressorMixin
import statsmodels.api as sm

class ExponentialDecayRegressor(BaseEstimator, RegressorMixin):
    """Fits an exponential decay curve
    """
    
    def __init__(self, starting_values=[1.,1.e-5,1.], **kwargs,):
        self.starting_values = starting_values

conormm

from sklearn.base import BaseEstimator, RegressorMixin
import statsmodels.api as sm

class QuantileRegression(BaseEstimator, RegressorMixin):
    """Sklearn wrapper for statsmodels Quantile Regression
    """
    def __init__(self, quantile=0.5, **kwargs):
        self.quantile = quantile
        self.kwargs = kwargs
        self.model = None