mzaradzki

exports.handler = (event, context, callback) => {
  
    var csd = new AWS.CloudSearchDomain({
        endpoint: CS_NAME+'.'+SERVICES_REGION+'.cloudsearch.amazonaws.com',
        apiVersion: '2013-01-01'
    });
  
    var params = {
        query: event.query,
        sort: '_score desc',

mzaradzki

exports.handler = (event, context, callback) => {
    
    // WARNING :
    // This snippet assumes : event.Records[0].eventName == 'ObjectCreated:Put'
    // but the ful code deals with both 'ObjectCreated:Put' and 'ObjectRemoved:Delete'
    
    var filename = event.Records[0].s3.object.key;
    var bucketname = event.Records[0].s3.bucket.name;
    
    var params = {

mzaradzki

from psutil import virtual_memory
from functools import wraps

MIN_VM_SHARE = 0.10
MAX_CRON_PROCESSES = 5

def cron_control(func=None):
    
    @wraps(func)
    def wrapped(*args, **kwargs):

mzaradzki

from time import localtime, mktime

MAX_RUN_MINUTES = 120

def cron_killer():
    
    def __run_minutes(proc):
        t_start = localtime(proc.create_time())
        t_now = localtime()
        return (mktime(t_now) - mktime(t_start)) / 60.

mzaradzki

from psutil import process_iter

def __get_cron_processes():
    processes = [proc for proc in process_iter() if ('python' == proc.name())]
    processes = [proc for proc in processes if ('python' in proc.cmdline())]
    processes = [proc for proc in processes if not(proc.username() is 'root')]
    processes = [proc for proc in processes if not('ipykernel' in proc.cmdline())]
    return processes

mzaradzki

# Search for variables that are very similar
def show_similars(cols, threshold=0.90):
    for i1, col1 in enumerate(cols):
        for i2, col2 in enumerate(cols):
            if (i1<i2):
                cm12 = pd.crosstab(dfX[col1], dfX[col2]).values # contingency table
                cv12 = cramers_corrected_stat(cm12) # Cramer V statistic
                if (cv12 > threshold):
                    print((col1, col2), int(cv12*100))

mzaradzki

# select columns that have "few" unique values
cramer_cols = [col for col in df.columns.values if (len(df[col].unique())<250)]

for col in cramer_cols:
    try:
        cm = pd.crosstab(df[col], df['status_group']).values # contingency table
        cv1 = cramers_corrected_stat(cm)
        if (cv1>=0.20):
            print(col, int(cv1*100))
    except:

mzaradzki

nbQs = 4 # quartiles
dfX['construction_year_quantile'] = pd.qcut(dfX['construction_year'], nbQs, labels=False)/(nbQs-1.0)

mzaradzki

# Before overwriting keep track of suspect rows with new binary columns
dfX['gps_height_bad'] = (dfX['gps_height']<=0)*1
geos.append('gps_height_bad')
dfX['longitude_bad'] = (dfX['longitude']<25)*1
geos.append('longitude_bad')
dfX['latitude_bad'] = (dfX['latitude']>-0.5)*1
geos.append('latitude_bad')

# Exemple of query via index=basin : mean_geo_df.at['Lake Victoria','latitude']
dfX.loc[dfX['gps_height']<=0, 'gps_height'] = dfX['basin'].apply(lambda x : mean_geo_df.at[x,'gps_height'])

mzaradzki

# bound of min/max latitude/longitude/height for Tanzania
bound_df = dfX[(dfX['latitude']<-0.5)&(dfX['longitude']>25)&(dfX['gps_height']>0)]

# mean of geographical data in each bucket
mean_geo_df = bound_df.groupby(['basin',])['latitude','longitude','gps_height'].mean()

assert(mean_geo_df.shape[0] == len(dfX['basin'].unique()))

# Out[31]: mean_geo_df
#                           latitude  longitude gps_height