georgedevasia

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

# Convert Series datatype to numeric (will error if column has non-numeric values)
# h/t @makmanalp
pd.to_numeric(df['Column Name'])

# Convert Series datatype to numeric, changing non-numeric values to NaN
# h/t @makmanalp for the updated syntax!

georgedevasia

# -*- coding: utf-8 -*-
"""
Created on Mon Mar  5 14:21:42 2018

@author: nilesh-tawari
email: tawari.nilesh@gmail.com
GitHub: https://github.com/nilesh-tawari
"""
from __future__ import print_function
import os

georgedevasia

import pandas as pd

# fix SettingWithCopyWarning: A value is trying to be set on a copy of a slice from a DataFrame. Either of following
pd.options.mode.chained_assignment = None  # default='warn'
df.is_copy = False


# read big csv
df = pd.read_csv(FILE_PATH, sep='\t', comment = '#', chunksize=1000, \
                low_memory=False, iterator = True, compression='gzip')

georgedevasia

# Create git repository and push to remote
cd workspace/Clinical_genomics_framework/
git init
git add .
git commit -m "Clinical genomics framework"
echo "# Clinical_genomics_framework" >> README.md
git add README.md
git commit -m "Readme file"

Create a repo online using browser  then push local to remote