arose13

import pandas as pd
from sklearn.base import BaseEstimator, RegressorMixin
from sklearn.preprocessing import OneHotEncoder
from sklearn.exceptions import NotFittedError


class StratifiedDummyRegressor(BaseEstimator, RegressorMixin):
    """
    An extremely scalable dummy regression model for computing the mean for each group specified by a column.

arose13

import xgboost as xgb

# Notice the large number of trees and the low learning rate.
# There are other important parameters like `subsample`, `min_child_weight` `colsample_bytree` but I'll leave that up
#   to you and grid searching.
gbm = xgb.XGBRFRegressor(n_estimators=10000, learning_rate=0.01, n_jobs=-1)

# Training with automatic termination
gbm.fit(
    x_train, y_train,

arose13

# Extremely high precision monte carlo estimation of pi
import numpy as np
import numpy.linalg as la
from sympy import N, pi


def calculate_pi():
    inside, n = 0, 1e6
    for i in range(int(n)):
        nth = i+1

arose13

arose13

#########################################################################################
### From Google Cloud Console
# from the navigation menu, under the Networking > VPC Network > Firewall rules

click 'CREATE FIREWALL RULE'
set Name
set Targets to 'All instances in the network'
set source IP range to '0.0.0.0/0'
set protocols and port to 'Allow all'
click create

arose13

# Kill all running containers
sudo docker kill $(sudo docker ps -q)

# Delete all stopped containers (This is the step that frees the most disk space)
sudo docker rm $(sudo docker ps -a -q)

# Delete all docker images
sudo docker rmi $(sudo docker images -q) 
 

arose13

# Setup Ubuntu
sudo apt update --yes
sudo apt upgrade --yes

# Get Miniconda and make it the main Python interpreter
wget https://repo.continuum.io/miniconda/Miniconda3-latest-Linux-x86_64.sh -O ~/miniconda.sh
bash ~/miniconda.sh -b -p ~/miniconda 
rm ~/miniconda.sh

export PATH=~/miniconda/bin:$PATH

arose13

    import csv
    
    def transpose_csv_out_of_core(csv_path, output_csv_path='transposed.csv', delimiter=','):
        """
        On my laptop it can transpose at ~375,000 lines a sec
        
        :param csv_path: 
        :param output_csv_path: 
        :param delimiter: 
        :return: 

arose13

def checkio(data):
    soln = {
        1: 'I',
        4: 'IV',
        5: 'V',
        9: 'IX',
        10: 'X',
        40: 'XL',
        50: 'L',
        90: 'XC',

arose13

def inverse_normal_cdf(p, mean, std):
    """
    This is the inverse to a normal distribution's CDF.

    While much slower this means you do not need Scipy as a project requirement.
    :param p: list of p = (0, 1)
    :param mean:
    :param std:
    :return:
    """