joaopcnogueira

% Package for subfloat
\usepackage{subfig}

% Figure with two sub-figures
\begin{figure}
\centering
\subfloat[caption of the figure goes here]
{
    \includegraphics[scale=.5]{fig-1.pdf}
    \label{fig:foo-1}

joaopcnogueira

import numpy as np
def latlon2km(latlon1,latlon2):
    # approximate radius of earth in km
    R = 6373.0

    lat1 = np.radians(latlon1[0])
    lon1 = np.radians(latlon1[1])
    lat2 = np.radians(latlon2[0])
    lon2 = np.radians(latlon2[1])

joaopcnogueira

import numpy as np
import statsmodels.formula.api as sm
def backward_elimination(X, y, sl):
    """
    X: the data matrix with the independent variables (predictors)
    y: the matrix of the dependent variable (target)
    sl: statistical level, by default the user should add 0.05 (5%)
    """
    X = np.append(arr=np.ones((len(X),1)).astype(int), values=X, axis=1)
    while(True):

joaopcnogueira

import numpy as np
import statsmodels.formula.api as sm
def backward_elimination2(X, y, sl):
    """
    X: the data matrix with the independent variables (predictors)
    y: the matrix of the dependent variable (target)
    sl: statistical level, by default the user should add 0.05 (5%)
    """
    X = np.append(arr=np.ones((len(X),1)).astype(int), values=X, axis=1)
    

joaopcnogueira

import re

my_string = "012.345.678-09"
digits_pattern = r"\d+"

digits = re.findall(digits_pattern, my_string)
number = int(''.join(digits))
print(number)

# output: 1234567809

joaopcnogueira

"""
Defining a custom function to be applied in pandas groupby
"""

import numpy as np
import pandas as pd

clients = ['joao', 'joao', 'joao', 'lucas', 'lucas', 'julia', 'julia', 'julia', 'julia']
products = ['smartphone', 'notebook', 'book', 'ball', 'car', 'hat', 'bike', 'mouse', 'pen']

joaopcnogueira

library(tidyverse)

# toy dataset
df <- tibble(
  clientes = c('joao', 'joao', 'joao', 'lucas', 'lucas', 'julia', 'julia', 'julia', 'julia'),
  produtos = c('celular', 'notebook', 'livro', 'bola', 'carro', 'chapéu', 'moto', 'moto', 'caneta')
)

# função customizada
get_produtos <- function(produtos){

joaopcnogueira

import numpy as np
import pandas as pd
from sklearn import datasets
from sklearn.tree import DecisionTreeClassifier
from sklearn.metrics import accuracy_score
from sklearn.model_selection import GroupKFold

# Loading the data
iris = datasets.load_iris()
design_matrix = np.concatenate((iris['data'], iris['target'].reshape(150,1)), axis=1)

joaopcnogueira

import pandas as pd
from sklearn.tree import DecisionTreeClassifier
from sklearn.model_selection import train_test_split
from sklearn.pipeline import Pipeline
from sklearn.impute import SimpleImputer
from category_encoders import OneHotEncoder

# lendo o dataset
df = pd.read_csv("train.csv")

joaopcnogueira

import pandas as pd
from sklearn.tree import DecisionTreeClassifier
from sklearn.model_selection import train_test_split
from sklearn.pipeline import Pipeline
from sklearn.impute import SimpleImputer
from category_encoders import OneHotEncoder
from sklearn.model_selection import KFold
from sklearn.model_selection import cross_validate

# lendo o dataset