oneryalcin

oneryalcin

oneryalcin

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [

oneryalcin

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [

oneryalcin

This small subclass of the Pandas sqlalchemy-based SQL support for reading/storing tables uses the Postgres-specific "COPY FROM" method to insert large amounts of data to the database. It is much faster that using INSERT. To acheive this, the table is created in the normal way using sqlalchemy but no data is inserted. Instead the data is saved to a temporary CSV file (using Pandas' mature CSV support) then read back to Postgres using Psychopg2 support for COPY FROM STDIN.

oneryalcin

######### ansible.cfg FILE ############

[defaults]
inventory = ./dev


######### DEV FILE ############
# Dev file
[servers]

oneryalcin

import nltk
nltk.download(['punkt', 'wordnet'])

import re
import numpy as np
import pandas as pd
from nltk.tokenize import word_tokenize
from nltk.stem import WordNetLemmatizer
from sklearn.metrics import confusion_matrix
from sklearn.model_selection import train_test_split

oneryalcin

import nltk
nltk.download(['punkt', 'wordnet', 'averaged_perceptron_tagger'])

import re
import pandas as pd
from nltk.tokenize import word_tokenize
from nltk.stem import WordNetLemmatizer
from sklearn.base import BaseEstimator, TransformerMixin

url_regex = 'http[s]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\(\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+'

oneryalcin

import nltk
nltk.download(['punkt', 'wordnet', 'averaged_perceptron_tagger'])

import re
import numpy as np
import pandas as pd
from nltk.tokenize import word_tokenize
from nltk.stem import WordNetLemmatizer

from sklearn.metrics import confusion_matrix

oneryalcin

# import libraries
from pyspark import SparkConf, SparkContext
from pyspark.sql import SparkSession, Window
from pyspark.sql.functions import count, when, isnan, isnull, desc_nulls_first, desc, \
    from_unixtime, col, dayofweek, dayofyear, hour, to_date, month
import pyspark.sql.functions as F
from pyspark.ml.feature import OneHotEncoderEstimator, StringIndexer, VectorAssembler, StandardScaler, MinMaxScaler
from pyspark.ml.classification import DecisionTreeClassifier, RandomForestClassifier

# sc = SparkContext(appName="Project_workspace")