ricgu8086

#!/bin/bash
sudo apt-get install -y \
    apt-transport-https \
    ca-certificates \
    curl \
    software-properties-common
curl -fsSL https://download.docker.com/linux/ubuntu/gpg | sudo apt-key add -
sudo apt-key fingerprint 0EBFCD88
sudo add-apt-repository \
   "deb [arch=amd64] https://download.docker.com/linux/ubuntu \

ricgu8086

def seed_everything(seed: int):
    import random, os
    import numpy as np
    import torch
    
    random.seed(seed)
    os.environ['PYTHONHASHSEED'] = str(seed)
    np.random.seed(seed)
    torch.manual_seed(seed)
    torch.cuda.manual_seed(seed)

ricgu8086

# From https://stackoverflow.com/questions/23586510/return-multiple-columns-from-pandas-apply

def sizes(s):    
    return locale.format("%.1f", s / 1024.0, grouping=True) + ' KB', \
        locale.format("%.1f", s / 1024.0 ** 2, grouping=True) + ' MB', \
        locale.format("%.1f", s / 1024.0 ** 3, grouping=True) + ' GB'
df_test['size_kb'],  df_test['size_mb'], df_test['size_gb'] = zip(*df_test['size'].apply(sizes))

ricgu8086

pivot.columns

MultiIndex([('mean', 'is_suitable'),
            ('size', 'is_suitable')],
           )

pivot.columns.map('_'.join)

Index(['mean_is_suitable', 'size_is_suitable'], dtype='object')

ricgu8086

def group_others(serie: pd.Series, 
                  min_threshold: int) -> pd.Series:
  """
  This function finds categorical values with little representation
  and group them under the category "OTHERS" to mitigate the curse
  of dimensionality, thus avoiding overfitting
  """
                 
  condition = (serie.value_counts() < min_threshold).values
  other_group = list(serie.value_counts()[condition].index)

ricgu8086

import pylab as plt

plt.plot([1,2,3,10], [1,2,3,4])
%matplot plt # Include this in the same cell as the plot

ricgu8086

def diversity_percentage(df, columns):
    """
    This function returns the number of different elements in each column as a percentage of the total elements in the group.
    A low value indicates there are many repeated elements.
    Example 1: a value of 0 indicates all values are the same.
    Example 2: a value of 100 indicates all values are different.
    """
    diversity = dict()

    for col in columns:

ricgu8086

def plot_nulls(dataframe):
    
    def null_perc(dataframe):
        return 100*dataframe.isnull().sum()/len(dataframe)
    
    nulls = null_perc(dataframe)
    plt.figure(1, figsize=(5,20)) # Customize this if needed
    ax = sns.barplot(x=nulls, y=list(range(len(nulls))), orient='h', color="blue")
    _ = plt.yticks(plt.yticks()[0], nulls.index)
    ax.xaxis.set_ticks_position('top')

ricgu8086

1. Clone your fork:

git clone [email protected]:YOUR-USERNAME/YOUR-FORKED-REPO.git

2. Add remote from original repository in your forked repository:

cd into/cloned/fork-repo
git remote add upstream git://github.com/ORIGINAL-DEV-USERNAME/REPO-YOU-FORKED-FROM.git
git fetch upstream

ricgu8086

from IPython.core.debugger import Tracer; 


# Place this call wherever you want to start debugging
Tracer()() 

"""
Some PDB Debuger commands:
n(ext) line and run this one
c(ontinue) running until next breakpoint