karishmadudani

import pandas as pd
import time
from datetime import datetime, timedelta
import datetime as dt
from datetime import date


data = {'col': ['id','Number of Days']}
ColumnList=pd.DataFrame(data=data)
today = date(2018, 6, 2)

karishmadudani

import pandas as pd
from sklearn.preprocessing import MinMaxScaler

#Import File
 your_dataset= pd.read_excel("Path\\FileName.xlsx")
 
 

karishmadudani

#Normalize variables between 0 & 1

VariableList = ['Number of Guests','Number of Bedrooms','Latitude','Longitude']
normVariableName = ['No_of_Guests_Norm','No_of_beds_norm','latitude_norm','longitude_norm']

scaler = MinMaxScaler()

for i in range(0,len(your_dataset)):
    for j in range(0,len(VariableList)):
        temp = your_dataset[VariableList[j]]

karishmadudani

lat = X_test[:,0]
lat = lat.reshape((len(lat),1))

lon = X_test[:,1]
lon = lon.reshape((len(lon),1))

time = X_test[:,2]
time = time.reshape((len(time),1))

print y_test.shape

karishmadudani

#split the data
X = RawData[[' Latitude (deg)', ' Longitude (deg)', 'time_secs']]
X = X.values.reshape((len(X),3))
y = RawData[' Vehicle speed (MPH)']
y = y.values.reshape((len(y),1))

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.001, random_state=42)

#Create the model and predict
nn = 40

karishmadudani

#Create a function to convert time variable to seconds
def hms_to_seconds(t):
    h, m, s = [float(j) for j in t.split(':')]
    return 3600*h + 60*m + s
    
#Read the raw files and extract the relevant variables    
RawData = pd.DataFrame()
for file in [f for f in os.listdir('C:\Users\lenovo\Desktop\Karishma\Project 2017\OBD\RawData') if f.endswith('.csv')]:
    filename = 'C:\Users\lenovo\Desktop\Karishma\Project 2017\OBD\RawData\\' + file
    data = pd.read_csv(filename, skiprows=2)

karishmadudani

import csv
import pandas as pd
import datetime as dt
from os import listdir
import os
import numpy as np
from numpy import mean, sqrt, square, arange
import matplotlib.pyplot as plt
from sklearn import neighbors
from sklearn.model_selection import train_test_split

karishmadudani

karishmadudani

# Join all the text from the 1000 tweets
Hashtag_Combined = " ".join(Htag_df['Hashtag'].values.astype(str))

no_millennials = " ".join([word for word in Hashtag_Combined.split()
                                if word != 'millennials'
                                and word != 'Millennials'
                                and word != 'Boomers'
                                and word != 'GenX'
                                                                
                                ])

karishmadudani

Htag_df = pd.DataFrame()
j = 0

for tweet in range(0,len(results)):
    hashtag = results[tweet].entities.get('hashtags')
    for i in range(0,len(hashtag)):
        Htag = hashtag[i]['text'] 
        Htag_df.set_value(j, 'Hashtag',Htag)
        j = j+1