hnykda

!SESSION 2014-12-13 12:58:37.593 -----------------------------------------------
eclipse.buildId=4.4.1.M20140925-0400
java.version=1.8.0_25
java.vendor=Oracle Corporation
BootLoader constants: OS=linux, ARCH=x86_64, WS=gtk, NL=en_US
Framework arguments:  -product org.eclipse.epp.package.standard.product
Command-line arguments:  -os linux -ws gtk -arch x86_64 -product org.eclipse.epp.package.standard.product

!ENTRY org.eclipse.equinox.p2.publisher.eclipse 4 0 2014-12-13 12:58:40.906
!MESSAGE Unable to acquire PluginConverter service during generation for: /usr/share/eclipse/plugins/colorer.

hnykda

def _load_data(data, n_prev = INIC):
    docX = []
    docY = []
    for i in range(len(data)-n_prev):
        docX.append(data.iloc[i:i+n_prev].as_matrix())
        docY.append(data.iloc[i+n_prev].as_matrix())
    alsX = np.array(docX)
    alsY = np.array(docY)
    
    return(alsX, alsY)

hnykda

""" From:  http://danielhnyk.cz/predicting-sequences-vectors-keras-using-rnn-lstm/ """
from keras.models import Sequential  
from keras.layers.core import TimeDistributedDense, Activation, Dropout  
from keras.layers.recurrent import GRU
import numpy as np

def _load_data(data, steps = 40):  
    docX, docY = [], []
    for i in range(0, data.shape[0]/steps-1):
        docX.append(data[i*steps:(i+1)*steps,:])

hnykda

----------------------------    LOGCAT    ----------------------------


--------- beginning of system
I/SystemServer(  765): NetworkTimeUpdateService
I/SystemServer(  765): CommonTimeManagementService
I/SystemServer(  765): CertBlacklister
I/SystemServiceManager(  765): Starting com.android.server.dreams.DreamManagerService
I/SystemServer(  765): Assets Atlas Service
I/SystemServiceManager(  765): Starting com.android.server.print.PrintManagerService

hnykda

import pandas as pd  
from random import random

flow = (list(range(1,10,1)) + list(range(10,1,-1)))*100
pdata = pd.DataFrame({"a":flow, "b":flow})  
pdata.b = pdata.b.shift(9)  
data = pdata.iloc[10:] * random()  # some noise  

import numpy as np

hnykda

----------------------------    LOGCAT    ----------------------------


--------- beginning of system
I/auditd  (    0): Starting up
I/audit_log(    0): Previous audit logfile detected, rotating
E/audit_rules(    0): Could not read audit rules /data/misc/audit/audit.rules: No such file or directory
I/irsc_util(    0): irsc tool created:0xb7048020
I/irsc_util(    0): Starting irsc tool
I/irsc_util(    0): Trying to open sec config file

hnykda

jan 07 07:30:39 rpielec systemd[1]: time has been changed
jan 07 07:30:42 rpielec kernel: usb 1-1.3: new high-speed usb device number 6 using dwc_otg
jan 07 07:30:42 rpielec kernel: bluetooth: core ver 2.21
jan 07 07:30:42 rpielec kernel: net: registered protocol family 31
jan 07 07:30:42 rpielec kernel: bluetooth: hci device and connection manager initialized
jan 07 07:30:42 rpielec kernel: bluetooth: hci socket layer initialized
jan 07 07:30:42 rpielec kernel: bluetooth: l2cap socket layer initialized
jan 07 07:30:42 rpielec kernel: bluetooth: sco socket layer initialized
jan 07 07:30:42 rpielec kernel: bluetooth: hci uart driver ver 2.3
jan 07 07:30:42 rpielec kernel: bluetooth: hci uart protocol h4 registered

hnykda

# priklad vstupniho XML souboru - je nutne si ho upravit dle sveho
"""<?xml version="1.0" encoding="UTF-8"?>
<Pisemnost nazevSW="EPO MF ČR" verzeSW="39.15.1">
    <DPHSHV verzePis="01.02">
        <VetaD d_poddp="29.03.2017" dokument="SHV" k_uladis="DPH" mesic="8" rok="2017" shvies_forma="R" />
        <VetaP c_pop="379" c_pracufo="2401" c_ufo="455" dic="<DIC>" jmeno="Daniel" naz_obce="<A>" prijmeni="<PRIJMENI>" psc="<PSC>" stat="ČESKÁ REPUBLIKA" titul="Bc." typ_ds="F" ulice="<ULICE>" />
        <VetaR c_rad="1" c_vat="<VAT>" k_pln_eu="3" k_stat="GB" pln_hodnota="<CASTKA>" pln_pocet="1" por_c_stran="1" />
    </DPHSHV>
    <Kontrola>
        <Uzivatel jmeno="null" prijmeni="null" />

hnykda

import os
from time import time
import pandas as pd
from memory_profiler import memory_usage

FILENAME='compressed_df'

def get_size(flnm):
    return round(os.path.getsize(flnm) / (1024*1024), 2)

hnykda

$ spss2py -v 0 execute data/q2-scripts-reduced/reduced/1.hdf data/q2-scripts-reduced/processed/2_statements.csv data/q2-scripts-reduced/processed/2_out.hdf
20170703 21:03:05:root:INFO - ######### STARTING #########
20170703 21:03:05:root:DEBUG - Received command line arguments: 
Namespace(data='data/q2-scripts-reduced/reduced/1.hdf', func=<function execute at 0x7f30159812f0>, output='data/q2-scripts-reduced/processed/2_out.hdf', statements=<_io.TextIOWrapper name='data/q2-scripts-reduced/processed/2_statements.csv' mode='r' encoding='UTF-8'>, verbosity=0)
<class 'pandas.core.frame.DataFrame'>
Int64Index: 72423 entries, 0 to 72422
Columns: 4861 entries, A1 to uid
dtypes: float16(4651), float32(7), int16(1), int8(184), object(18)
memory usage: 667.7+ MB
20170703 21:03:07:spss2py.executer:DEBUG -