BrunoGomesCoelho

wget https://repo.anaconda.com/archive/Anaconda3-5.2.0-Linux-x86_64.
sh Anaconda3-5.2.0-Linux-x86_64.sh
conda update -n base conda

# Activate a environment then inside it run:
conda install pandas matplotlib jupyter notebook scipy scikit-learn nb_conda seaborn 

# Add some extra things...
# jupyter extensions
conda install -c conda-forge jupyter_contrib_nbextensions

BrunoGomesCoelho

from multiprocessing import Pool # for reading the CSVs faster

def my_read_csv(filename):
    # Helper function for the parellel load_csvs
    return pd.read_csv(filename)

def load_csvs(prefix):
    """Reads and joins all our CSV files into one big dataframe.
    We do it in parallel to make it faster, since otherwise it takes some time.
    Idea from: https://stackoverflow.com/questions/36587211/easiest-way-to-read-csv-files-with-multiprocessing-in-pandas

BrunoGomesCoelho

# taken from https://stackoverflow.com/a/20538655
git init
git remote add origin PATH/TO/REPO
git fetch
git checkout -t origin/master

BrunoGomesCoelho

"""Famous kaggle reduce mem usage script.

NOT MINE - taken from https://www.kaggle.com/gemartin/load-data-reduce-memory-usage
"""

import pandas as pd
import numpy as np

def reduce_mem_usage(df):
    """ iterate through all the columns of a dataframe and modify the data type

BrunoGomesCoelho

def embed_plotly(fig):
    """
    See https://plotly.com/python/static-image-export/
    """
    # not sure if this import will work outside jupyter
    from IPython.display import Image
    img_bytes = fig.to_image(format="png")
    return Image(img_bytes)