saraswatmks

import numpy as np
import random


def gradient_descent(alpha, x, y, ep=0.0001, max_iter=10000):
    converged = False
    iter = 0
    m = x.shape[0] # number of samples

    # initial theta

saraswatmks

path <- "/home//Desktop/MLC01/"
setwd(path)

# Load data and libraries -------------------------------------------------

library(data.table)
library(h2o)
library(caret)
library(stringr)
library(e1071)

saraswatmks

library(data.table)
library(jsonlite)

#### Train
train <- fromJSON("train_data.json")

train_data <- data.table(ID = unlist(names(train)))
train_data[, `:=` (genres = unlist(lapply(train, '[',1)),
                   titles = unlist(lapply(train, '[',2)),

saraswatmks

# coding: utf-8

import json
import pandas as pd
file_name_1 = "train_data.json"
with open(file_name_1, 'r') as jsonfile1:
    data_dict_1 = json.load(jsonfile1)
    
file_name_2 = "test_data.json"
with open(file_name_2, 'r') as jsonfile2:

saraswatmks

table_1 = pd.DataFrame({'Slab_ID': np.repeat('1_1',19), 'ActCastLength':np.arange(1.1,3,0.1)})

table_2 = pd.DataFrame({'Slab_ID': ['1_1','1_1'], 'DefectStart_Y':[1.5,2.3],\
                        'DefectEnd_Y':[1.8,2.5], 'Defective':[1,1]})

for c in np.arange(2):
    table_1['Defective' + str(c)] = table_1['ActCastLength'].between(table_2.loc[c,'DefectStart_Y'],\
                                                                     table_2.loc[c, 'DefectEnd_Y'])
    table_1['Defective' + str(c)] = [1 if x == True else 0 for x in table_1['Defective'+str(c)]]
    

saraswatmks

library(data.table)

sdata <- fread("address_data.csv")
head(sdata)

setnames(sdata,"x","address")

# some cleaning
sdata$pincodes := unlist(regmatches(address, gregexpr("(\\d+){6}",sdata$address)))]
sdata$address := gsub(pattern = "(\\d+){6}",replacement = "", x = sdata$address)]

saraswatmks

# coding: utf-8

# load libary - you might need to install xlrd library in case it throws any error in reading file
import pandas as pd


# read file
sensor = pd.read_excel("SENSOR-009.xlsx",sheetname="Sheet1")

saraswatmks

#!/usr/bin/env python

import csv
import json
import sys
import numpy as np


LOCAL = True

saraswatmks

def calculate_ndcg(test_movies, predicted_movies, already_watched):
	partial_dcgs = []
	predicted_event_flags = {}
	actual_events = test_movies
	for pred_index, predicted_event in enumerate(predicted_movies):
		try:
			last_occ = predicted_event_flags.get(predicted_event, -1)
			actual_index = actual_events[last_occ+1:].index(predicted_event)
			effective_index = actual_index + last_occ + 1
			predicted_event_flags[predicted_event] = effective_index

saraswatmks

#include <iostream>
#include <cstring>

using namespace std;

void parseDot(char s[100], int &first, int &second) {
    int length = strlen(s);
    int temp = 0, dotFound = 0, negative = 1;
    for (int i = 0; i < length; i++) {
        if (s[i] == '.') {