3. Statistics

nums = [872, 432, 397, 427, 388, 782, 397]

def mean(x):

    return sum(x) / len(x)

print("Mean: ", mean(nums))

from math import * # a library that provides math functions

nums = [872, 432, 397, 427, 388, 782, 397]

def median(x):

    if (len(x) % 2 == 1):

        return sorted(x)[int(floor(len(x)/2))]

    else:

        a = int(floor(len(x)/2-1))

        b = int(floor(len(x)/2))

        return (sorted[a] + sorted[b]) / 2

print("Median: ", median(nums))

nums = [872, 432, 397, 427, 388, 782, 397]

def mode(l): # assuming l is non empty

    d = {}

    for x in l:

        if (x in d):

            d[x] +=1

        else:

            d[x] = 1

    print(d)

    #print(d.items())

    sorted_pairs = sorted(d.items(), key=lambda p:-p[1]) #-p[1] to sort in descending order

    #print(sorted_pairs)

    #print(sorted_pairs[0])

    (_mode,count) = sorted_pairs[0] # (_mode,count) is key & value (Dictionary)

    return (_mode if count != 1 else None)

print("Mode: ", mode(nums))

nums = [872, 432, 397, 427, 388, 782, 397]

def variance(l):  # assuming l is non empty

    m = mean(l)

    diffsqsum = sum(map(lambda x: (x - m) ** 2, l)) # map is the loop

    return diffsqsum / len(l)

print("Variance: ",variance(nums))

nums = [872, 432, 397, 427, 388, 782, 397]

def std(l):  # assuming l is non empty

    return sqrt(variance(l))

print("Standard deviation: ",std(nums))

import pandas as pd

dataVal = [(10,20,30,40,50,60,70),

           (10,10,40,40,50,60,70),

           (10,20,30,50,50,60,80)]

dataFrame = pd.DataFrame(data=dataVal)

skewValue = dataFrame.skew(axis=1)

print("DataFrame:")

print(dataFrame)

print("Skew:")

print(skewValue)

import pandas as pd

import numpy as np

dataMatrix = [(65,75,74,73,95,76,62,100),

              (101,102,103,107,157,160,191,192)]

print("Data:")

dataFrame = pd.DataFrame(data=dataMatrix)

print(dataFrame)

print("Kurtosis:")

kurt = dataFrame.kurt(axis=1)

print(kurt)

import pandas as pd

import numpy as np

dataMatrix2 = [(70,90,90,100,120,120,100,121,125,115,112),

              (58.22,39.33,-30.44,36.77,20.80,-73.95,-39.99,91.03,-138.01,-20,None)];

print("Data2: ");

dataFrame2 = pd.DataFrame(data=dataMatrix2)

print(dataFrame2);

print("Kurtosis 2:");

kurt2 = dataFrame2.kurt(axis=1)

print(kurt2);

import pandas as pd

df = pd.read_csv("p3_data2.tsv", "\t")

print(df.head())

s=df['Part-time Labour costs']

print("Type: ", type(s))

print("Mean: ", s.mean())

print("Median: ", s.median())

print("Mode: ", s.mode())

print("Min: ", s.min())

print("Max: ",s.max())