VinACE

## pyspark_interactive_with_datastax_connector.py
## invoking pyspark as follows: ##
# /path/to/spark-1.2.0-bin-hadoop2.4/bin/pyspark --jars /path/to/spark-1.2.0-bin-hadoop2.4/jars/spark-cassandra-connector-assembly-1.2.0-SNAPSHOT.jar
# first, stop the spark context launched by pyspark to avoid the conflict
sc.stop()

from py4j.java_gateway import java_import
from pyspark import SparkConf

conf = (SparkConf()
         .setMaster("local")

## df2json.py
"""
tiny script to convert a pandas data frame into a JSON object
"""

import ujson as json
import pandas
import numpy as np

df = pandas.DataFrame({
    "time" : [1,2,3,4,5],

## INSTALL
###### development tools
sudo apt-get install build-essential python-dev git nodejs-legacy npm gnome-tweak-tool openjdk-8-jdk

### Python packages
sudo apt-get install python-pip python-virtualenv python-numpy python-matplotlib

### pip packages

pip install django flask django-widget-tweaks django-ckeditor beautifulsoup4 requests classifier SymPy ipython

## world-index.json
{
  "aliases":{},
  "warmers":{},
  "mappings": {
    "world": {
      "properties": {
        "capital": {
          "properties": {
            "district": {
              "type": "string"

## csv_to_elastic_search_bulk_insert.py
from pyelasticsearch import ElasticSearch
import pandas as pd
from time import time

root_path="/home/clemsos/Dev/mitras/"
raw_data_path=root_path+"data/"
csv_filename="week10.csv"

t0=time()

## useful_pandas_snippets.py
# multiply/divide
df['quantity'] = df['quantity'].apply(lambda x: x*-1)

# round function on dataframe
df['quantity'] = df['quantity'].apply(lambda x: round(x, 2))

# List unique values in a DataFrame column
# h/t @makmanalp for the updated syntax!
df['Column Name'].unique()

## classifier_from_little_data_script_1.py
'''This script goes along the blog post
"Building powerful image classification models using very little data"
from blog.keras.io.
It uses data that can be downloaded at:
https://www.kaggle.com/c/dogs-vs-cats/data
In our setup, we:
- created a data/ folder
- created train/ and validation/ subfolders inside data/
- created cats/ and dogs/ subfolders inside train/ and validation/
- put the cat pictures index 0-999 in data/train/cats

## classifier_from_little_data_script_2.py
'''This script goes along the blog post
"Building powerful image classification models using very little data"
from blog.keras.io.
It uses data that can be downloaded at:
https://www.kaggle.com/c/dogs-vs-cats/data
In our setup, we:
- created a data/ folder
- created train/ and validation/ subfolders inside data/
- created cats/ and dogs/ subfolders inside train/ and validation/
- put the cat pictures index 0-999 in data/train/cats

## classifier_from_little_data_script_3.py
'''This script goes along the blog post
"Building powerful image classification models using very little data"
from blog.keras.io.
It uses data that can be downloaded at:
https://www.kaggle.com/c/dogs-vs-cats/data
In our setup, we:
- created a data/ folder
- created train/ and validation/ subfolders inside data/
- created cats/ and dogs/ subfolders inside train/ and validation/
- put the cat pictures index 0-999 in data/train/cats

## docker_cheat_sheet.sh
#################################################################################
# Authors: Keiller Nogueira, Victor de Melo
#################################################################################

# nvidia-docker seems more stable now and several images are starting to adopt it (including
# [kaixhin](https://github.com/NVIDIA/nvidia-docker/issues/85).
# hence, we suggest to use it instead, as it solves a few issues with gpu passthrough.
# usage: it is only required when creating a container, i.e, with `run` and related arguments
# you're not required to provide $DOCKER_NVIDIA_DEVICES as it will find the devices itself
	## invoking pyspark as follows: ##
	# /path/to/spark-1.2.0-bin-hadoop2.4/bin/pyspark --jars /path/to/spark-1.2.0-bin-hadoop2.4/jars/spark-cassandra-connector-assembly-1.2.0-SNAPSHOT.jar
	# first, stop the spark context launched by pyspark to avoid the conflict
	sc.stop()

	from py4j.java_gateway import java_import
	from pyspark import SparkConf

	conf = (SparkConf()
	.setMaster("local")
	"""
	tiny script to convert a pandas data frame into a JSON object
	"""

	import ujson as json
	import pandas
	import numpy as np

	df = pandas.DataFrame({
	"time" : [1,2,3,4,5],
	###### development tools
	sudo apt-get install build-essential python-dev git nodejs-legacy npm gnome-tweak-tool openjdk-8-jdk

	### Python packages
	sudo apt-get install python-pip python-virtualenv python-numpy python-matplotlib

	### pip packages

	pip install django flask django-widget-tweaks django-ckeditor beautifulsoup4 requests classifier SymPy ipython
	{
	"aliases":{},
	"warmers":{},
	"mappings": {
	"world": {
	"properties": {
	"capital": {
	"properties": {
	"district": {
	"type": "string"
	from pyelasticsearch import ElasticSearch
	import pandas as pd
	from time import time

	root_path="/home/clemsos/Dev/mitras/"
	raw_data_path=root_path+"data/"
	csv_filename="week10.csv"

	t0=time()
	# multiply/divide
	df['quantity'] = df['quantity'].apply(lambda x: x*-1)

	# round function on dataframe
	df['quantity'] = df['quantity'].apply(lambda x: round(x, 2))

	# List unique values in a DataFrame column
	# h/t @makmanalp for the updated syntax!
	df['Column Name'].unique()
	'''This script goes along the blog post
	"Building powerful image classification models using very little data"
	from blog.keras.io.
	It uses data that can be downloaded at:
	https://www.kaggle.com/c/dogs-vs-cats/data
	In our setup, we:
	- created a data/ folder
	- created train/ and validation/ subfolders inside data/
	- created cats/ and dogs/ subfolders inside train/ and validation/
	- put the cat pictures index 0-999 in data/train/cats
	#################################################################################
	# Authors: Keiller Nogueira, Victor de Melo
	#################################################################################

	# nvidia-docker seems more stable now and several images are starting to adopt it (including
	# [kaixhin](https://github.com/NVIDIA/nvidia-docker/issues/85).
	# hence, we suggest to use it instead, as it solves a few issues with gpu passthrough.
	# usage: it is only required when creating a container, i.e, with `run` and related arguments
	# you're not required to provide $DOCKER_NVIDIA_DEVICES as it will find the devices itself