# This Python 3 environment comes with many helpful analytics libraries installed
# It is defined by the kaggle/python docker image: https://github.com/kaggle/docker-python
# For example, here's several helpful packages to load in 

#import numpy as np # linear algebra
#import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)

# Input data files are available in the "../input/" directory.
# For example, running this (by clicking run or pressing Shift+Enter) will list the files in the input directory

#import os
#print(os.listdir("../input"))

# Any results you write to the current directory are saved as output.

rm(list=ls())

suppressMessages(library(data.table))
suppressMessages(library(DT))
suppressMessages(library(timeSeries))
suppressMessages(library(tidyverse))
suppressMessages(library(reshape))
suppressMessages(library(stringr))
suppressMessages(library(doBy))
suppressMessages(library(formattable))
suppressMessages(library(gridExtra))

suppressMessages(library(ggplot2))
suppressMessages(library(plotly))
suppressMessages(library(corrplot))
suppressMessages(library(wesanderson))
suppressMessages(library(RColorBrewer))
suppressMessages(library(gridExtra))
suppressMessages(library(zoo))

suppressMessages(library(forecast))
suppressMessages(library(prophet)) ### For Prophet Forecasting
suppressMessages(library(nnfor))    ### For Neural Network Forecasting

set.seed(2018)


train=fread("../input/train.csv")
sprintf("The train data set has %d rows and %d columns", nrow(train), ncol(train) )
str(train)

test  <- fread("../input/test.csv")
sprintf("The test data set has %d rows and %d columns", nrow(test), ncol(test) )
str(test)

print("the summary of train sales is:")
summary(train$sales)


train$Year=year(train$date)        #returns the year from date i.e. 2013, 2014 etc.
train$Month=as.yearmon(train$date) #this yearmon() function is coming from zoo package

# Check missing data in Columns
colSums(is.na(train))

# Growth by Date

MSP <- aggregate(sales ~date, train, mean)

sl1 <-ggplot(MSP, aes(x=as.factor(date), y=sales))
#+
 # geom_line(color=gbp1, size=1.5)+
  #geom_point(colour=gbp1, size = 3.5, alpha=0.5)+
  #labs(title="The Growth of Sale Prices by date", x=NULL, y="Sale Price")+
  #theme( plot.title=element_text(vjust=3, size=15) ) + theme_minimal()