ivankeller

#!/bin/bash

# Workaround script to copy from hdfs file system to NAS
# solving permission limitation at writing on NAS directly with hdfs command
#
# Usage:
# $ hdfs2Nas <full path> <destination directory>

SOURCE=$1
DEST=$2

ivankeller

#!/bin/bash
# Recreate a user that was created previously
# TODO: this onworking script has the side effect of setting the ownership badly on user with
# previous same userid. Must be fixed.


# create user
username=$1
adduser $username --home /data/users/$username

ivankeller

def belongs_to(t, a, b):
    """Return True if t belongs to real number interval [a, b], False otherwise."""
    return t >= a and t <= b

def is_in_arc(t, a, b, m=365):
    """Return True if t is in the interval [a, b] modulo m, False otherwise"""
    t, a, b = [x % m for x in (t, a, b)]    # convert all the values to their values modulo m
    if a < b: 
        return belongs_to(t, a, b)
    else: 

ivankeller

import pandas as pd
import numpy as np

def describe_df(df, cols=None, max_distinct=10):
    """Describe columns of given dataframe.
    
    Return a dataframe with column name, type, nb of distinct values and nb of missing values
    Missing values are counted as one distinct value.
    
    Issue: if a column contains integer and missing values, pandas cast it in float and add .0 to the value.

ivankeller

import pandas as pd
import numpy as np

def describe_df(df, cols=None, max_distinct=10):
    """Describe columns of given dataframe.
    
    Return a dataframe with column name, type, nb of distinct values and nb of missing values
    Missing values are counted as one distinct value.
    
    Issue: if a column contains integer and missing values, pandas cast it in float and add .0 to the value.

ivankeller

def dataframe_constructor(df):
    return "df = pd.DataFrame(%s)" % (str(df.to_dict()).replace("nan"," float('nan')").replace('array', 'np.array'))

ivankeller

import pytest
import numpy as np

def r_cut(x0: float, x1: float, r: float) -> (float, float):
    """Return y0, y1 such that y1/y0 = r, y0<x0, y1<x1 and y0+y1 is maximum.
    
    Parameters
    ----------
    x0, x1 > 0
    r >= 0 and <= 1

ivankeller

$ cd my_project  #where Pipfile resides
$ pipenv install ipykernel
$ pipenv shell  #if not already done before
(my-virtualenv-name) $ python -m ipykernel install --user --name=my-virtualenv-name
(my-virtualenv-name) $ jupyter lab  #or jupyter notebook

ivankeller

#!/usr/bin/env python
import boto3

s3client = boto3.client('s3')

response = s3client.list_buckets()
for bucket in response['Buckets']:
    print(f"""\'{bucket['Name']}\',""")

ivankeller

#!/usr/bin/env python

# for listing and selecting the buckets you want to delete use list_s3_buckets.py gist

import boto3

# list of the bucket names you want to delete
BUCKETS_TO_DELETE = []

def delete_versioned_bucket(s3resource, bucket_name):