AllieUbisse

#!/bin/bash
########################################################################################
#                                   START, STOP or STATUS                              #
#                               ----------------------------                           #
#       This scrip is intended to help you start, stop or get the IP address of        #
#       Current running EC2.                                                           #
#       This will require you to 1st configure your AWC-CLI, namualy to ensure safety  #
#                                                                                      #
#       Please read the code to ensure that It does not cause any security issues      #
#                                                                                      #

AllieUbisse

#!/bin/bash


##################################################################################
#     ----------------------------------------------------------------
#     THIS SCRIPT WILL HELP YOUR AUTOMATE THE DOCKER INSTALATION STEPS
#     ----------------------------------------------------------------
# Test was ran on aws ec2 instance. 
#
# AUTHOR:

snehamehrin

#Import All Functions
from pyspark.sql import SQLContext
from pyspark.sql import functions as F
from pyspark.sql import SparkSession
from pyspark.sql.functions import unix_timestamp, to_date, date_format, month, year, dayofyear, dayofweek, col
from pyspark.sql.types import TimestampType
from pyspark.sql import functions as F
from pyspark.sql import SparkSession
from pyspark.sql.functions import unix_timestamp, to_date, date_format, month, year, dayofyear, dayofweek, col
from pyspark.sql.types import TimestampType

carlleston

Ben-Epstein

liorshk

def log_run(gridsearch: sklearn.GridSearchCV, experiment_name: str, model_name: str, run_index: int, conda_env, tags={}):
    """Logging of cross validation results to mlflow tracking server
    
    Args:
        experiment_name (str): experiment name
        model_name (str): Name of the model
        run_index (int): Index of the run (in Gridsearch)
        conda_env (str): A dictionary that describes the conda environment (MLFlow Format)
        tags (dict): Dictionary of extra data and tags (usually features)

jeanmidevacc

from sklearn.neighbors import KNeighborsRegressor
from sklearn.metrics import mean_squared_error, mean_absolute_error, r2_score, explained_variance_score

import mlflow
import mlflow.sklearn

import numpy as np

# Launch the experiment on mlflow
experiment_name = "electricityconsumption-forecast"

ldrewniak

azarnyx

oskarryn

'''
spark/bin/spark-submit \
    --master local --driver-memory 4g \
    --num-executors 2 --executor-memory 4g \
    --packages org.apache.spark:spark-sql-kafka-0-10_2.11:2.4.0 \
    sstreaming-spark-final.py
'''
from pyspark.sql import SparkSession
from pyspark.sql.types import *
from pyspark.sql.functions import expr