
import numpy as np
import pandas as pd


d=pd.read_csv("C:\\Users\\Anirudh\\Desktop\\onlinefoods.csv")


df=pd.DataFrame(d)
print(d)

     Age  Gender Marital Status Occupation  Monthly Income  \
0     20  Female         Single    Student       No Income   
1     24  Female         Single    Student  Below Rs.10000   
2     22    Male         Single    Student  Below Rs.10000   
3     22  Female         Single    Student       No Income   
4     22    Male         Single    Student  Below Rs.10000   
..   ...     ...            ...        ...             ...   
383   23  Female         Single    Student       No Income   
384   23  Female         Single    Student       No Income   
385   22  Female         Single    Student       No Income   
386   23    Male         Single    Student  Below Rs.10000   
387   23    Male         Single    Student       No Income   

    Educational Qualifications  Family size  latitude  longitude  Pin code  \
0                Post Graduate            4   12.9766    77.5993    560001   
1                     Graduate            3   12.9770    77.5773    560009   
2                Post Graduate            3   12.9551    77.6593    560017   
3                     Graduate            6   12.9473    77.5616    560019   
4                Post Graduate            4   12.9850    77.5533    560010   
..                         ...          ...       ...        ...       ...   
383              Post Graduate            2   12.9766    77.5993    560001   
384              Post Graduate            4   12.9854    77.7081    560048   
385              Post Graduate            5   12.9850    77.5533    560010   
386              Post Graduate            2   12.9770    77.5773    560009   
387              Post Graduate            5   12.8988    77.5764    560078   

    Output   Feedback Unnamed: 12  
0      Yes   Positive         Yes  
1      Yes   Positive         Yes  
2      Yes  Negative          Yes  
3      Yes   Positive         Yes  
4      Yes   Positive         Yes  
..     ...        ...         ...  
383    Yes   Positive         Yes  
384    Yes   Positive         Yes  
385    Yes   Positive         Yes  
386    Yes   Positive         Yes  
387    Yes   Positive         Yes  

[388 rows x 13 columns]


type(df)

pandas.core.frame.DataFrame


df['Gender'].dtype

dtype('O')


df.head()


df.tail()


print(df.describe())

              Age  Family size    latitude   longitude       Pin code
count  388.000000   388.000000  388.000000  388.000000     388.000000
mean    24.628866     3.280928   12.972058   77.600160  560040.113402
std      2.975593     1.351025    0.044489    0.051354      31.399609
min     18.000000     1.000000   12.865200   77.484200  560001.000000
25%     23.000000     2.000000   12.936900   77.565275  560010.750000
50%     24.000000     3.000000   12.977000   77.592100  560033.500000
75%     26.000000     4.000000   12.997025   77.630900  560068.000000
max     33.000000     6.000000   13.102000   77.758200  560109.000000


df["Age"].min()

18


df["Age"].max()

33


df.apply(lambda x : x)


df.apply(lambda x : x[0])

Age                                      20
Gender                               Female
Marital Status                       Single
Occupation                          Student
Monthly Income                    No Income
Educational Qualifications    Post Graduate
Family size                               4
latitude                            12.9766
longitude                           77.5993
Pin code                             560001
Output                                  Yes
Feedback                           Positive
Unnamed: 12                             Yes
dtype: object


df.sort_values("Monthly Income",ascending=True)


df.sort_values(by="Marital Status")


df.value_counts("Marital Status")

Marital Status
Single               268
Married              108
Prefer not to say     12
dtype: int64


df.sort_values(by="Occupation")
df.value_counts("Occupation")

Occupation
Student           207
Employee          118
Self Employeed     54
House wife          9
dtype: int64


df.sort_values(by="Feedback")
df.value_counts("Feedback")

Feedback
Positive     317
Negative      71
dtype: int64


df.groupby('Output').size()

Output
No      87
Yes    301
dtype: int64


import seaborn as sns
sns.countplot(df['Output'],label="Count")

C:\Users\Anirudh\anaconda3\lib\site-packages\seaborn\_decorators.py:36: FutureWarning: Pass the following variable as a keyword arg: x. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.
  warnings.warn(

<AxesSubplot:xlabel='Output', ylabel='count'>


sns.countplot(df['Feedback'],label="Count")

C:\Users\Anirudh\anaconda3\lib\site-packages\seaborn\_decorators.py:36: FutureWarning: Pass the following variable as a keyword arg: x. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.
  warnings.warn(

<AxesSubplot:xlabel='Feedback', ylabel='count'>


df.groupby('Occupation').size()

Occupation
Employee          118
House wife          9
Self Employeed     54
Student           207
dtype: int64


df.groupby('Educational Qualifications').size()

Educational Qualifications
Graduate         177
Ph.D              23
Post Graduate    174
School            12
Uneducated         2
dtype: int64


from matplotlib import pyplot
%matplotlib inline
df.hist(figsize=(12,10))
pyplot.show()


df.plot(kind='density', subplots=True, layout=(3,3), sharex=False,figsize=(12,10))
pyplot.show()


df.plot(kind='box', subplots=True, layout=(3,3), sharex=False, sharey=False,figsize=(12,10))
pyplot.show()


import pandas
from pandas.plotting import scatter_matrix

dataCorr = df.corr()
pandas.plotting.scatter_matrix(dataCorr,figsize=(12,10))
pyplot.show()


df['Unnamed: 12'].value_counts(normalize=True)

Yes    0.775773
No     0.224227
Name: Unnamed: 12, dtype: float64


df['Unnamed: 12'].value_counts().plot.bar()

<AxesSubplot:>


df['Gender'].value_counts().plot.bar()

<AxesSubplot:>


import matplotlib.pyplot as plt


df['Gender'].value_counts(normalize=True).plot.bar(title= 'Gender')

<AxesSubplot:title={'center':'Gender'}>


df['Marital Status'].value_counts(normalize=True).plot.bar(title= 'Marital Status')

<AxesSubplot:title={'center':'Marital Status'}>


df['Educational Qualifications'].value_counts(normalize=True).plot.bar(title='Educational Qualifications')

<AxesSubplot:title={'center':'Educational Qualifications'}>


df['Educational Qualifications'].value_counts(normalize=True).plot.line(title='Educational Qualifications')

<AxesSubplot:title={'center':'Educational Qualifications'}>


df['Age'].value_counts(normalize=True).plot.line(title='Age')

<AxesSubplot:title={'center':'Age'}>


table = pd.pivot_table(data=df,index=['Gender'])
table

	Age	Family size	Pin code	latitude	longitude
Gender
Female	24.415663	3.409639	560038.819277	12.974443	77.603669
Male	24.788288	3.184685	560041.081081	12.970274	77.597535

	Age	Gender	Marital Status	Occupation	Monthly Income	Educational Qualifications	Family size	latitude	longitude	Pin code	Output	Feedback	Unnamed: 12
0	20	Female	Single	Student	No Income	Post Graduate	4	12.9766	77.5993	560001	Yes	Positive	Yes
1	24	Female	Single	Student	Below Rs.10000	Graduate	3	12.9770	77.5773	560009	Yes	Positive	Yes
2	22	Male	Single	Student	Below Rs.10000	Post Graduate	3	12.9551	77.6593	560017	Yes	Negative	Yes
3	22	Female	Single	Student	No Income	Graduate	6	12.9473	77.5616	560019	Yes	Positive	Yes
4	22	Male	Single	Student	Below Rs.10000	Post Graduate	4	12.9850	77.5533	560010	Yes	Positive	Yes

	Age	Gender	Marital Status	Occupation	Monthly Income	Educational Qualifications	Family size	latitude	longitude	Pin code	Output	Feedback	Unnamed: 12
253	22	Male	Single	Employee	10001 to 25000	Graduate	2	12.9299	77.6848	560103	Yes	Positive	Yes
35	25	Male	Single	Student	10001 to 25000	Post Graduate	3	12.9306	77.5434	560085	Yes	Positive	Yes
273	24	Female	Married	Employee	10001 to 25000	Post Graduate	2	12.9561	77.5921	560027	Yes	Positive	Yes
187	25	Male	Single	Employee	10001 to 25000	Graduate	2	12.9757	77.5586	560023	Yes	Positive	Yes
279	23	Female	Prefer not to say	Employee	10001 to 25000	Graduate	4	12.9048	77.6821	560036	Yes	Positive	Yes
...	...	...	...	...	...	...	...	...	...	...	...	...	...
157	32	Female	Married	House wife	No Income	Graduate	3	12.9850	77.5533	560010	Yes	Positive	Yes
159	20	Female	Single	Student	No Income	Graduate	2	12.9337	77.5900	560011	Yes	Positive	Yes
160	21	Male	Single	Student	No Income	Graduate	2	12.9337	77.5900	560011	Yes	Positive	Yes
133	19	Male	Single	Student	No Income	Graduate	2	13.0019	77.5713	560003	No	Negative	No
387	23	Male	Single	Student	No Income	Post Graduate	5	12.8988	77.5764	560078	Yes	Positive	Yes

	Age	Gender	Marital Status	Occupation	Monthly Income	Educational Qualifications	Family size	latitude	longitude	Pin code	Output	Feedback	Unnamed: 12
290	27	Female	Married	Self Employeed	More than 50000	Graduate	6	13.0734	77.5464	560014	No	Positive	No
278	30	Male	Married	Employee	More than 50000	Graduate	5	12.9719	77.5128	560072	No	Negative	No
130	28	Male	Married	Employee	More than 50000	Post Graduate	3	13.0019	77.5713	560003	Yes	Positive	Yes
131	32	Female	Married	Employee	More than 50000	Graduate	1	13.0019	77.5713	560003	No	Positive	No
276	24	Male	Married	Employee	More than 50000	Post Graduate	3	12.9515	77.4921	560056	Yes	Positive	Yes
...	...	...	...	...	...	...	...	...	...	...	...	...	...
129	23	Female	Single	Student	No Income	Post Graduate	4	13.0487	77.5923	560024	Yes	Positive	Yes
128	23	Male	Single	Student	No Income	Post Graduate	3	12.9770	77.5773	560009	Yes	Positive	Yes
127	25	Male	Single	Student	No Income	Post Graduate	4	12.9770	77.5773	560009	Yes	Positive	Yes
122	26	Female	Single	Self Employeed	25001 to 50000	Post Graduate	3	12.9635	77.5821	560002	Yes	Positive	Yes
387	23	Male	Single	Student	No Income	Post Graduate	5	12.8988	77.5764	560078	Yes	Positive	Yes