10/19/21, 8:56 AM Untitled3.

ipynb - Colaboratory

import pandas as pd

import numpy as np

import seaborn as sns

import matplotlib.pyplot as plt

from pandas.plotting import autocorrelation_plot

from scipy import stats
plt.style.use("ggplot")

import warnings

warnings.filterwarnings("ignore")
from scipy import stats

url_data = "https://raw.githubusercontent.com/supasonicx/ATA-praktikum-01/main/Starbucks%2
data = pd.read_csv(url_data)

data.head()

chaseCoffee itempurchaseCold itemPurchasePastries itemPurchaseJuices itemPurchaseS

1 1 1 1

1 1 1 1

1 1 1 1

1 1 1 1

1 1 1 1

data.shape

(113, 33)

data.columns

Index(['Id', 'gender', 'age', 'status', 'income', 'visitNo', 'method',

'timeSpend', 'location', 'membershipCard', 'itemPurchaseCoffee',

'itempurchaseCold', 'itemPurchasePastries', 'itemPurchaseJuices',

'itemPurchaseSandwiches', 'itemPurchaseOthers', 'spendPurchase',

'productRate', 'priceRate', 'promoRate', 'ambianceRate', 'wifiRate',

'serviceRate', 'chooseRate', 'promoMethodApp', 'promoMethodSoc',

'promoMethodEmail', 'promoMethodDeal', 'promoMethodFriend',

'promoMethodDisplay', 'promoMethodBillboard', 'promoMethodOthers',

'loyal'],

dtype='object')

data['gender'].unique()

array([1, 0])

plt.figure(figsize=(20,10))

https://colab.research.google.com/drive/1qVPMTOdz4eXyXMKL6SFtxrUYWmhJZAVK#scrollTo=-2nyy2bdQ1Yn&uniqifier=1 1/6
10/19/21, 8:56 AM Untitled3.ipynb - Colaboratory

<Figure size 1440x720 with 0 Axes>

plt.figure(figsize=(20,10))

plt.title('Histogram of timeSpend')

sns.histplot(data,x='...', kde=True)

---------------------------------------------------------------------------

ValueError Traceback (most recent call last)

<ipython-input-17-576c17bd502c> in <module>()

1 plt.figure(figsize=(20,10))

2 plt.title('Histogram of timeSpend')

----> 3 sns.histplot(data,x='...', kde=True)

4 frames
/usr/local/lib/python3.7/dist-packages/seaborn/_core.py in _assign_variables_longfor
901

902 err = f"Could not interpret value `{val}` for parameter `{ke
--> 903 raise ValueError(err)

904

905 else:

ValueError: Could not interpret value `...` for parameter `x`

SEARCH STACK OVERFLOW

## ploting untuk data produk pastry 

m = plt.hist(data[data["gender"] == 1].itemPurchasePastries,bins=30,fc = (1,0,0,0.5),label
##ploting untuk data tumor dengan label jinak

f = plt.hist(data[data["gender"] == 0].itemPurchasePastries,bins=30,fc = (0,1,0,0.5),label
plt.legend()

https://colab.research.google.com/drive/1qVPMTOdz4eXyXMKL6SFtxrUYWmhJZAVK#scrollTo=-2nyy2bdQ1Yn&uniqifier=1 2/6
10/19/21, 8:56 AM Untitled3.ipynb - Colaboratory

plt.xlabel("Nilai itemPurchasePastries")

plt.ylabel("Frequency")
plt.title("Histogram Pembelian produk pastry bedasarkan demografi gender")

plt.show()

 ## Menghitung nilai outliers dari variabel timeSpend pada data customer dengan gender lak
male = data[data["gender"] == 1]

female = data[data["gender"] == 0]

desc = male.timeSpend.describe()

Q1 = desc[4]

Q3 = desc[6]

IQR = Q3-Q1

lower_bound = Q1 - 1.5*IQR

upper_bound = Q3 + 1.5*IQR

print("Apa pun di luar kisaran ini adalah outlier timeSpend: (", lower_bound ,",", upper_b
male[male.timeSpend < lower_bound].timeSpend

print("Outliers: ",male[(male.timeSpend < lower_bound) | (male.timeSpend > upper_bound)].t

Apa pun di luar kisaran ini adalah outlier timeSpend: ( -1.5 , 2.5 )

Outliers: [4]

## Menghitung nilai outliers dari variabel visitNo (jumlah kedatangan) pada data customer 
male = data[data["gender"] == 1]

female = data[data["gender"] == 0]

desc = data.<<??>>.describe()

Q1 = desc[4]

Q3 = desc[6]

IQR = Q3-Q1

lower_bound = Q1 - 1.5*IQR

upper_bound = Q3 + 1.5*IQR

print("Apa pun di luar kisaran ini adalah outlier visitNo: (", lower_bound ,",", upper_bou
female[female.timeSpend < lower_bound].timeSpend

print("Outliers: ",female[(male.timeSpend < lower_bound) | (female.timeSpend > upper_bound

https://colab.research.google.com/drive/1qVPMTOdz4eXyXMKL6SFtxrUYWmhJZAVK#scrollTo=-2nyy2bdQ1Yn&uniqifier=1 3/6
10/19/21, 8:56 AM Untitled3.ipynb - Colaboratory

File "<ipython-input-31-126ddc38fe97>", line 4

desc = data.<<??>>.describe()
^

## variabel male menyimpan data yang ada pada seluruh kolom dengan nilai gender = 1

SyntaxError: invalid syntax

male = data[data["gender"] == 1]

## variabel female menyimpan data yang ada pada seluruh kolom dengan nilai gender = 0

SEARCH STACK OVERFLOW

print("mean: ",<<2.407407>>.<<2.407407>>.mean())

print("variance: ",<<0.6610761705101328>>.<<0.6610761705101328>>.var())

print("standart deviation (std): ",<< 0.8130659078513456>>.<< 0.8130659078513456>>.std())
print("describe method: ",<<54.000000>>.<<54.000000>>.describe())

File "<ipython-input-32-8f34908708e4>", line 5

print("mean: ",<<2.407407>>.<<2.407407>>.mean())

SyntaxError: invalid syntax

SEARCH STACK OVERFLOW

mean_diff = male.visitNo.mean() - female.visitNo.mean()

var_male = male.visitNo.var()

var_female = female.visitNo.var()
var_pooled = (len(male)*var_male +len(female)*var_female )  /float(len(male)+ len(female))
effect_size = mean_diff/np.sqrt(var_pooled)

print("Effect size: ",effect_size)

Effect size: 0.40638112114512326

## Relationship Between Variables - Korelasi

* Kita dapat mengatakan bahwa dua variabel terkait satu sama lain, jika salah satunya memb
* Misalnya, harga dan jarak. Jika Anda pergi jarak jauh dengan taksi Anda akan membayar le
* Scatter Plot, Cara termudah untuk memeriksa hubungan antara dua variabel

* Matriks korelasi besar yang mencakup banyak angka

* Kisaran angka ini adalah -1 hingga 1. 

* Arti dari 1 adalah dua variabel yang saling berkorelasi positif seperti mean radius dan 
* Arti dari nol adalah tidak ada korelasi antara variabel seperti productRate dengan incom
* Arti dari -1 adalah dua variabel berkorelasi negatif satu sama lain seperti income dan m

File "<ipython-input-34-e8ec6617507c>", line 2

* Kita dapat mengatakan bahwa dua variabel terkait satu sama lain, jika salah sa
yang lain\n",

SyntaxError: invalid syntax

SEARCH STACK OVERFLOW

f,ax=plt.subplots(figsize = (11, 9))

dfs = data.loc[:,['productRate','priceRate','serviceRate','visitNo','timeSpend','wifiRate'
sns.heatmap(dfs.corr(),annot= True,linewidths=0.5,fmt = ".1f",ax=ax)

bottom, top = ax.get_ylim()

ax.set_ylim(bottom + 0.5, top - 0.5)

plt.xticks(rotation=90)

plt.yticks(rotation=0)

https://colab.research.google.com/drive/1qVPMTOdz4eXyXMKL6SFtxrUYWmhJZAVK#scrollTo=-2nyy2bdQ1Yn&uniqifier=1 4/6
10/19/21, 8:56 AM Untitled3.ipynb - Colaboratory

plt.title('Correlation Map')

plt.savefig('graph.png')

plt.show()

print("Covariance diantara timeSpend dan income: ",data.timeSpend.cov(data.<<??>>))

print("Covariance diantara timeSpend dan visitNo: ",data.timeSpend.cov(data.<<??>>))"

File "<ipython-input-36-6fb6de043c1e>", line 1

print("Covariance diantara timeSpend dan income: ",data.timeSpend.cov(data.<<??>

SyntaxError: invalid syntax

SEARCH STACK OVERFLOW

p1 = data.loc[:,["gender","serviceRate"]].corr(method= "pearson")

p2 = data.serviceRate.cov(data.timeSpend)(data.serviceRate.std()*data.timeSpend.std())

print('Pearson correlation: ')

print(p1)

print('Pearson correlation: ',p2)

https://colab.research.google.com/drive/1qVPMTOdz4eXyXMKL6SFtxrUYWmhJZAVK#scrollTo=-2nyy2bdQ1Yn&uniqifier=1 5/6
10/19/21, 8:56 AM Untitled3.ipynb - Colaboratory

---------------------------------------------------------------------------

TypeError Traceback (most recent call last)

<ipython-input-37-e5795f5e9419> in <module>()

1 p1 = data.loc[:,["gender","serviceRate"]].corr(method= "pearson")

----> 2 p2 = data.serviceRate.cov(data.timeSpend)
(data.serviceRate.std()*data.timeSpend.std())

3 print('Pearson correlation: ')

4 print(p1)

5 print('Pearson correlation: ',p2)

TypeError: 'numpy.float64' object is not callable

SEARCH STACK OVERFLOW

ranked_data = data.rank()
spearman_corr = ranked_data.loc[:,["timeSpend","serviceRate"]].corr(method= "pearson")
print("Spearman's correlation: ")
print(spearman_corr)

Spearman's correlation:

timeSpend serviceRate

timeSpend 1.000000 -0.092361

serviceRate -0.092361 1.000000

statistic, p_value = stats.ttest_rel(data.gender,data.productRate)
print('p-value adalah: ',p_value)

p-value adalah: 9.83197741893934e-60

check 0 d selesai pada 08.56

https://colab.research.google.com/drive/1qVPMTOdz4eXyXMKL6SFtxrUYWmhJZAVK#scrollTo=-2nyy2bdQ1Yn&uniqifier=1 6/6