dyerrington

grep -v '^[ \t]*$\|^[ \t]*#' /etc/ssh/sshd_config

dyerrington

find . -type d -name .ext | xargs rm -rf

dyerrington

find . -type f -print0 | xargs -0 cat | wc -w

dyerrington

sql_df[np.abs(sql_df['score'].values - sql_df['score'].values.mean())<=(3*sql_df['score'].values.std())]

dyerrington

import numpy as np, pandas as pd, os, seaborn as sns, codecs
from gensim import corpora, models, similarities 
from gensim.parsing.preprocessing import STOPWORDS

class preprocess_corpus(object):
    
    files  =  []
    dirs   =  []
    
    def __init__(self, dir, directory=False, stopwords_file=False):

dyerrington

import bisect
import random

def Mean(t):
    """Computes the mean of a sequence of numbers.

    Args:
        t: sequence of numbers

    Returns:

dyerrington

import numpy as np
import scipy as sp
import scipy.stats

def mean_confidence_interval(data, confidence=0.95):
    a = 1.0*np.array(data)
    n = len(a)
    m, se = np.mean(a), scipy.stats.sem(a)
    h = se * sp.stats.t._ppf((1+confidence)/2., n-1)
    return m, m-h, m+h

dyerrington

from geopy.geocoders import Bing

geolocator  =   Bing("your key here")
location = geolocator.geocode('your location here')
try:
    if not location: continue
        geo_location = {
            'origin_address': location.address,
            'origin_latitude': location.latitude,
            'origin_longitude': location.longitude

dyerrington

#Step1, convert Time after loading:
ufo = pd.read_csv('https://raw.githubusercontent.com/sinanuozdemir/SF_DAT_17/master/data/ufo.csv')   # can also read csvs directly from the web!
ufo['Time'] = ufo['Time'].apply(pd.to_datetime)


# Step 2:  Group by unique days
ufo.groupby([pd.Grouper(key='Time',freq='1D')])[['Shape Reported']].count()

# Also, you can concat Year, Month, and Day into a new feature, and group by that.  As an engineer, I much prefer to work on strict types and leverage current method.

dyerrington

def auto_coefficients(df):
    
    sorted_coefs  =   list()
    coefs         =   df.corr()
    
    for row_index, row_values in enumerate(coefs.values):
        
        for col_index, col_value in enumerate(row_values):
            
            if coefs.columns[row_index] == coefs.columns[col_index]: