Sandy4321

Data preparation

-- set mapred.max.split.size=128000000;
set hive.input.format=org.apache.hadoop.hive.ql.io.CombineHiveInputFormat;
set hive.tez.input.format=org.apache.hadoop.hive.ql.io.CombineHiveInputFormat;
set hive.mapjoin.smalltable.filesize=30000000;
-- set hive.optimize.s3.query=true;
set hive.exec.dynamic.partition.mode=nonstrict; 
set hive.optimize.sort.dynamic.partition=false;

Sandy4321

bitcoin = cryptos[0]
bitcoin_cash = cryptos[1]
dash = cryptos[2]
ethereum_classic = cryptos[3]
bitconnect = cryptos[4]
litecoin = cryptos[5]
monero = cryptos[6]
nem = cryptos[7]
neo = cryptos[8]
numeraire = cryptos[9]

Sandy4321

#!/usr/bin/env python
# coding: utf-8

# ## Perform Chi-Square test for Bank Churn prediction (find out different patterns on customer leaves the bank)  . Here I am considering only few columns to make things clear

# ### Import libraries

# In[2]:

Sandy4321

SELECT m.* FROM #matches m
INNER JOIN #matches m1 ON m.fromid = m1.toid AND m.toid = m1.fromid AND m1.fromid <=m1.toid
ORDER BY m.toteam

Sandy4321

SELECT t.id fromid,t.Team fromteam,t1.id toid,t1.Team toteam
INTO #matches
FROM #Team t
INNER JOIN #Team t1 ON t.id <> t1.id

SELECT * FROM #matches

Sandy4321

Sandy4321

# more than 3 -> 1, less than 5 -> 0
data_df['preference'] = np.where(data_df['rating'] > 3, 1, 0)
data_df.head()

Sandy4321

Sandy4321

Sandy4321