project 1

#1

The data describes what is likely the average Math and Verbal SAT scores per state. (I say average because I can't be certain from the data where the values we're derived)

#2

The data has an extra row 'ALL' that was a problem throughout my code. I realized I should have removed it earlier. I had a similar problem where I was forced to use .pop which I didn't like because if the code was ran again it would throw off the data moving forward (I made a note on #6). Additionally, Nebraska's state abbreviation was wrong which mean's nothing now until you get to the bonus.

#3

I wasn't sure what this was asking...

#4

import csv

allData = []
with open ('/Users/Paul/Desktop/General_Assembly/DSI_SM_01/projects/01-projects-weekly/project-01/assets/sat_scores.csv') as f:
    reader = csv.reader(f)
    for row in reader:
        allData.append(row[0:4])

#5

print allData

#6

###can only run this once....###

lables = allData.pop(0)
print lables

#7

states = [s[0] for s in allData]
print states

#8

for index, val in enumerate(allData[2]):
    print lables[index], type(allData[2][index])

#9

for h in allData:
    h[1] = int(h[1])
    h[2] = int(h[2])    
    h[3] = int(h[3])    
    
print allData
    

#10

rate = [s[1] for s in allData]
verbal = [s[2] for s in allData]
mathL = [s[3] for s in allData]

dicRate = {}
for index, value in enumerate(allData):
    dicRate[states[index]] = allData[index][1]

dicMath = {}
for index, value in enumerate(allData):
    dicMath[states[index]] = allData[index][2]

dicVerbal = {}
for index, value in enumerate(allData):
    dicVerbal[states[index]] = allData[index][3]
    
    
print 'Rate', dicRate    
print 'Math', dicMath
print 'Verbal', dicVerbal

#11

scores = {states[i]: allData[i] for i, state in enumerate(states)}
print scores

#12

import numpy as np

minRate = np.min(rate)
maxRate = np.max(rate)

minVerbal = np.min(verbal)
maxVerbal = np.max(verbal)

minMath = np.min(mathL)
maxMath = np.max(mathL)

print "min: Rate" , minRate 
print "max: Rate" , maxRate
print "min: Verbal" , minVerbal
print "max: Verbal" , maxVerbal
print "min: Math" , minMath
print "max: Math" , maxMath 


#13

import math as mt

rateAverage = sum(rate)/51
rateNewList = []

for i in rate[0:50]:
    result = (rateAverage - i) ** 2
    rateNewList.append(result)

rateStd = mt.sqrt(sum(rateNewList)/51)
    
verbalAverage = sum(verbal)/51
verbalNewList = []

for x in verbal[0:50]:
    result2 = (verbalAverage - x) ** 2
    verbalNewList.append(result2)

verbalStd = mt.sqrt(sum(verbalNewList)/51)
mathAverage = sum(mathL)/ 51

mathNewList = []

for y in mathL[0:50]:
    result3 = (mathAverage - x) ** 2
    mathNewList.append(result3)

mathStd = mt.sqrt(sum(mathNewList)/51)

print "rate: std" , rateStd
print "verbal: std" , verbalStd
print "math: std " , mathStd




#14

import matplotlib.pyplot as plt
import numpy as np
%matplotlib inline

plt.hist(rate[0:50])
plt.show()


#15

plt.hist(mathL)
plt.show()

#16

plt.hist(verbal)
plt.show()

#17

That it is a Normal Distribution

#18

No

#19

plt.scatter(verbal, mathL)
plt.show()

plt.scatter(mathL, verbal)
plt.show()

plt.scatter(rate, mathL)
plt.show()

plt.scatter(rate, verbal)
plt.show()



#20 

plt.scatter(rate, mathL)
plt.show()

plt.scatter(rate, verbal)
plt.show()

Math and Verbal scores show a pattern of decreasing in relation to rate. In other words, the more students that take the SATS per state, the more likely the scores will represent a normal distribution. However, in some states, the SATS are not taken except for students wishing to attend universities requiring an SAT scores for admission.

#21

plt.boxplot(rate)
plt.show()

plt.boxplot(verbal)
plt.show()

plt.boxplot(mathL)
plt.show()

#22

I created 2 views in project1FINAL tableu file.

1st - Using information from data.gov on 2014 State education budgets, I hypothesized that the more a state would invest in education the greater the state SAT scores would be. 

2nd - Comparing Math and Verbal total SAT scores by State