alejio

jupyter-nbconvert --to slides MySlideshow.ipynb --reveal-prefix=reveal.js

alejio

# Add and commit all
git add -A && git commit -m "Your Message"
# Push to branch
git push -u origin <branch>
# undo commit
git reset HEAD~
# remove tracked file
git rm --cached

alejio

#Assumed imports:

import pandas as pd
#John Galt's answer is basically a reduce operation. If I have more than a handful of dataframes, I'd put them in a list like this (generated via list comprehensions or loops or whatnot):

dfs = [df0, df1, df2, dfN]
#Assuming they have some common column, like name in your example, I'd do the following:

df_final = reduce(lambda left,right: pd.merge(left,right,on='name'), dfs)
#That way, your code should work with whatever number of dataframes you want to merge.

alejio

library("RSQLite")
# connect to the sqlite file
con = dbConnect(RSQLite::SQLite(), dbname="database.sqlite")
# get a list of all tables
alltables = dbListTables(con)
# get tables as df
df.country = dbGetQuery( con,'select * from Country' )

alejio

import pandas as pd
from sqlalchemy import create_engine # database connection
import datetime as dt
from IPython.display import display
import matplotlib
import numpy as np
import matplotlib.pyplot as plt
pd.set_option('display.max_columns', 120)
%matplotlib inline

alejio

library(data.table)
library(bnlearn)

df <- fread("file.csv", sep="|", verbose=TRUE)

cols <- colnames(df, 3:24)
df <- as.data.frame(df)
df_temp <- data.frame(apply(df, 2, as.factor))
df <- df_temp
rm(df_temp)

alejio

def supervised_learner(df, clf, train_list, testsize = 0.3, predictors=df.columns[1:], target=df.columns[-1]):
    ### Import packages
    from sklearn.cross_validation import train_test_split
    from sklearn import linear_model
    from sklearn.linear_model import SGDClassifier
    from sklearn.metrics import confusion_matrix
    from sklearn.metrics import classification_report
    import pandas as pd
    import numpy as np
    from sklearn.metrics import roc_curve

alejio

def df_get_dummies(df, drops, cats, pkey=None, binary=1):
    
    ### Import packages
    import pandas as pd
    import numpy as np
    ###
    
    # The following columns aren't used in modelling so drop
    df = df.drop(drops, 1)
    # Ensure BPE and LE are categories before getting dummies

alejio

df_out = pd.DataFrame(columns=df.columns)
df_temp = pd.DataFrame(columns=df.columns)
for elem in a_list:
    df_temp =  df[df.pkey==elem]
    if len(df_temp) > a_number:
        df_temp_ind = df_temp.index.map(lambda x: x if np.random.binomial(1, prob_keep)==1 else None)
        df_temp = df_temp.loc[df_temp_ind,].dropna()
    else:
        pass
    df_out = df_out.append(df_temp, ignore_index=True)

alejio

# Inspired from here http://stackoverflow.com/questions/7015587/python-difference-of-2-datetimes-in-months 
from datetime import datetime, timedelta
from calendar import monthrange
def monthdelta(df):
    d1 = df[0]
    d2 = df[1]
    delta = 0
    while True:
        mdays = monthrange(d1.year, d1.month)[1]
        d1 += timedelta(days=mdays)