jmquintana79

import pandas as pd
from sklearn.preprocessing import FunctionTransformer
from sklearn.pipeline import Pipeline
# example
from sklearn.linear_model import LogisticRegression

# X, y

def get_dummies_size(df):
    return pd.get_dummies(df, columns=['size'])

jmquintana79

import pandas as pd
import numpy as np
from sklearn.pipeline import Pipeline
from sklearn.compose import ColumnTransformer
# example models and preprocessors
from sklearn.preprocessing import StandardScaler, OneHotEncoder
from sklearn.impute import SimpleImputer
from sklearn.linear_model import LogisticRegression

# X, y

jmquintana79

Reference: https://hydra.cc/docs/patterns/configuring_experiments/

config.ymal

defaults:
  - db: mysql
  - server: apache

db/mysql.ymal

jmquintana79

class Credentials():

    def __init__(self):
        self.user = "user"
        self.password = "password"


class Service(Credentials):
    def __init__(self):
        super().__init__()

jmquintana79

import pandas as pd

## unstack a timeseries target variable according to a categorical reference column 
def unstack_ts_according_to_reference(df:pd.DataFrame, c_dt:str, c_cat_reference:str, c_target_variable:str)->pd.DataFrame:
    """
    Unstack a timeseries target variable according to a categorical reference column.
    df -- Dataframe to be processed.
    c_dt -- Temporal column.
    c_cat_reference -- Categorical column to be used as reference to stack the target variable.
    c_target_variable -- Num / Cat column to be stacked.

jmquintana79

from scipy.stats import linregress
# estimate linear regression y = Ax + B
A, B, r_value, p_value, std_err = linregress(x, y)

jmquintana79

# original column
In [15]: df["timedelta_column"]
Out[15]: 
0    1 days 00:00:00
1    3 days 02:00:00
2    5 days 04:00:00
3    7 days 06:00:00
4    9 days 08:00:00
5   11 days 10:00:00
dtype: timedelta64[ns]

jmquintana79

import os
extension = os.path.splitext(filename)[1]

jmquintana79

import os

if os.path.isfile("filename.txt"):
    # file exists
    f = open("filename.txt")

if os.path.isdir("data"):
    # directory exists

if os.path.exists(file_path):

jmquintana79

import numpy as np

## angle format: 0/360 to -180/180
def angles_format(angle_0_360:np.array)->np.array:
    return np.array([v-360 if v>=180 else v for v in angle_0_360])

## aggregation for angular data
def angles_agg(angle_0_360:np.array, func_agg) -> float:
    """
    Calculate wind direction average.