otaviomguerra

apiVersion: v1
kind: Pod
metadata:
  name: ubuntu-debug
spec:
  containers:
  - name: ubuntu
    image: ubuntu:latest
    # Just spin & wait forever
    command: [ "/bin/bash", "-c", "--" ]

otaviomguerra

import tensorflow as tf

def set_gpu_memory_limit(memory_limit=6096):
    """Set limit to GPU memory usage.

    from https://github.com/tensorflow/tensorflow/issues/43174#issuecomment-782222166
    Parameters
    ----------
    memory_limit : int, optional
        Amount of memory to use in MegaBytes, by default 6096 MB (6GB)

otaviomguerra

MongoDB Cheat Sheet

Show All Databases

show dbs

Show Current Database

otaviomguerra

title	subtitle	author	date	source
Docker Compose Cheatsheet	Quick reference for Docker Compose commands and config files	Jon LaBelle	April 7, 2019	https://jonlabelle.com/snippets/view/markdown/docker-compose-cheatsheet

Basic config example

otaviomguerra

#!/usr/bin/env python3

'''
Thanks to Andres Torres
Source: https://www.pythoncentral.io/introduction-to-sqlite-in-python/
'''

import sqlite3

# Create a database in RAM

otaviomguerra

import tensorflow as tf
import argh
# see: https://github.com/tensorflow/tensorflow/issues/46107

def quantize_model(
    original_model_path='models/best-model.h5',
    quantized_model_path='models/quantized_model.tflite'):
    """Converts .h5 model to .tflite by applying 
    quantization.

otaviomguerra

# pip install func-timeout
from func_timeout import func_timeout, FunctionTimedOut

try:
    func_result = func_timeout(10, func, args=(arg1, arg2))
except FunctionTimedOut:
    print("The function could not complete within 10 seconds, hence terminated.\n")
except Exception as e:
    print(f"ERROR: {e} on executing the function")

otaviomguerra

from pandas.testing import assert_frame_equal

assert_frame_equal(df1, df2, check_dtype=False)

otaviomguerra

import pyspark.sql.functions as F


def count_missings(spark_df, sort=True):
    """
    Counts number of nulls and nans in each column
    """
    df = spark_df.select(
        [
            F.count(F.when(F.isnan(c) | F.isnull(c), c)).alias(c)

otaviomguerra

from pyspark.ml import Pipeline
from pyspark.ml.regression import GBTRegressor
from pyspark.ml.feature import VectorAssembler, StandardScaler
from pyspark.ml.evaluation import RegressionEvaluator

# Get the names of the input features
input_cols = df.columns[:-1]

# Rename target col and split the dataset
df = df.withColumnRenamed('target_column_original_name', 'label')