FavioVazquez

*.md
*.html
*.pdf
libraries

FavioVazquez

FavioVazquez

# Import optimus
import optimus as op
# Instanciate DataFrameTransfomer
transformer = op.DataFrameTransformer(df)
# Get original dataFrame to show it.
transformer.show()
# Chaining function transformations
transformer.trim_col("*")
           .remove_special_chars("*")
           .clear_accents("*")

FavioVazquez

# Import optimus
import optimus as op
# Choose a column for analyzing
detector = op.OutlierDetector(df,"num")
# With the outliers() method you can use MAD to detect if there is an outlier in your column
detector.outliers()
# And with the run() method you can see which values are not outliers
detector.run()
# Finally with the delete_outliers() method you can delete existing outliers in your column. 
# This will modify the dataframe we have used when instantiating the OutlierDetector

FavioVazquez

# Import optimus
import optimus as op
transformer = op.DataFrameTransformer(df)
# Choose the columns to run the analysis and the names of the columns for the output
transformer.impute_missing(["a","b"],["out_a","out_B"],strategy="mean").show()
# Choose the columns to run the analysis and the names of the columns for the output
transformer.impute_missing(["a","b"],["out_a","out_B"],strategy="median").show()

FavioVazquez

# Import optimus
import optimus as op
# Instance of Utilities class
tools = op.Utilities()
# Reading df from web
url = "https://raw.githubusercontent.com/ironmussa/Optimus-examples/master/examples/foo.csv"
df = tools.read_dataset_url(path=url)

FavioVazquez

# Import optimus
import optimus as op
# Instance of Utilities class
tools = op.Utilities()
# Reading DF from web
url = "https://raw.githubusercontent.com/ironmussa/Optimus-examples/master/examples/foo.csv"
df = tools.read_dataset_url(path=url)

FavioVazquez

# Instance of transformer class 
transformer = op.DataFrameTransformer(df)

FavioVazquez

import findspark
findspark.init("/opt/spark")
import random
from pyspark import SparkContext
sc = SparkContext(appName="EstimatePi")
def inside(p):
    x, y = random.random(), random.random()
    return x*x + y*y < 1
NUM_SAMPLES = 1000000
count = sc.parallelize(range(0, NUM_SAMPLES)) \

FavioVazquez

!curl -O http://download.tensorflow.org/example_images/flower_photos.tgz
!tar xzf flower_photos.tgz
!mkdir flower_photos/sample