Sales Data Analysis¶

In [3]:
import os
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
import plotly.graph_objs as go
import plotly.offline as iplot
In [4]:
pwd
Out[4]:
'/Users/mac'
In [5]:
ls

 Sales Data Analysis.ipynb
@github.com/
Applications/
Betty/
Data Science Week 2 Case Study.ipynb
Data clearing with python.ipynb
Desktop/
Diabetic Data.ipynb
Documents/
Downloads/
Example.ipynb
Library/
Matplotlib Class.ipynb
Movies/
Music/
PANDAS Data Frames.ipynb
Pictures/
Public/
PycharmProjects/
Seaborn libary.ipynb
Untitled.ipynb
Untitled1.ipynb
Untitled2.ipynb
Untitled3.ipynb
Untitled4.ipynb
Untitled5.ipynb
Untitled6.ipynb
Week 1 Case Study  Managing Student Information .ipynb
alx-low_level_programming/
alx-low_level_programming-1/
alx-pre_course/
alx-system_engineering-devops/
alx-zero_day/
anaconda3/
bash/
c/
cryptex/
figure2.png
js/
pandas intro.ipynb
pandas.ipynb
testwork.ipynb
zero_day/
In [6]:
cd desktop

/Users/mac/Desktop
In [7]:
ls

000DF646-332C-4B8E-8CF1-0E0891E48743.MP4
0e663a72-2ce6-4df5-a1ab-1230f421d46d.MP4
10-check_cycle.c
10-linked_lists.c
10fd4c9f-75ea-4484-abfe-ab433840f0aa.JPG
142aaef7-c25d-4645-be6a-7b00f0c23ee6.JPG
1c930d9e-542d-4d98-9bdd-482671ffc878.JPG
2129c1c1-3b61-41a2-bf13-7fbe5a7127b4.JPG
2767fe65-1fa4-47f3-818e-94f179fd1f53.JPG
2D35F7B0-0587-476E-9240-2C54EF12E34C.JPG
3-print_alphabt.py
364c8528-7c86-48e7-a4f6-50f0eaf23242.JPG
3f5d533b-9fce-4ea8-ada1-989be8513652.JPG
43a7dac6-00c0-40b5-afd1-1b5ddec7929f.JPG
450dc9d1-4c2f-404c-8313-82573120b61e.JPG
46203242-b471-4f7e-808e-f32e425f0edd.JPG
7d7d185e-93f9-415c-b59a-751aa2ffaff0.JPG
7ec45444-f0a1-4ab4-9a57-705ab20aad26.JPG
924dfd31-4380-4891-b14d-4998650c9315.JPG
AMP Access Account.pdf
C FILES/
House_of_the_Dragon_S01E05_480p_WEB-DL_RMTeam.mkv
IMG_4685.HEIC
IMG_4798.MOV
IMG_4799.MOV
IMG_4800.MOV
IMG_4838.MOV
IMG_4839.MOV
IMG_4840.MOV
IMG_4848.MOV
IMG_4849.MOV
IMG_4850.MOV
IMG_4851.MOV
IMG_4852.MOV
IMG_4853.MOV
IMG_4930.HEIC
IMG_4931.HEIC
IMG_4932.HEIC
IMG_4933.HEIC
IMG_4934.HEIC
IMG_4935.HEIC
IMG_4936.HEIC
IMG_4937.HEIC
IMG_4938.HEIC
IMG_4939.HEIC
IMG_4940.HEIC
IMG_4941.HEIC
IMG_4942.MOV
IMG_4943.HEIC
IMG_4944.HEIC
IMG_4945.HEIC
IMG_4946.HEIC
IMG_4947.HEIC
IMG_4948.HEIC
IMG_4949.HEIC
IMG_4950.HEIC
IMG_4951.HEIC
IMG_4952.HEIC
IMG_4953.HEIC
IMG_4954.HEIC
IMG_4955.HEIC
IMG_4956.HEIC
IMG_4957.HEIC
IMG_4958.HEIC
IMG_4959.HEIC
IMG_4960.HEIC
IMG_4961.HEIC
IMG_4962.HEIC
IMG_4963.HEIC
IMG_4964.HEIC
IMG_4965.HEIC
IMG_4966.HEIC
IMG_4967.HEIC
IMG_4968.HEIC
IMG_4969.HEIC
IMG_4970.HEIC
IMG_4971.HEIC
IMG_4972.HEIC
IMG_4973.HEIC
IMG_4974.HEIC
IMG_4975.HEIC
IMG_4976.HEIC
IMG_4977.HEIC
IMG_4978.HEIC
IMG_4979.HEIC
IMG_4980.HEIC
IMG_4981.HEIC
IMG_4982.HEIC
IMG_4983.HEIC
IMG_4984.HEIC
IMG_4985.HEIC
IMG_4986.HEIC
IMG_4987.HEIC
IMG_4988.HEIC
IMG_4989.HEIC
IMG_4990.HEIC
IMG_4991.HEIC
IMG_4992.HEIC
IMG_4993.HEIC
IMG_4994.HEIC
IMG_4995.HEIC
IMG_4996.HEIC
IMG_4997.HEIC
IMG_4998.HEIC
IMG_4999.HEIC
IMG_5001.HEIC
IMG_5002.HEIC
IMG_5003.HEIC
IMG_5004.HEIC
IMG_5005.HEIC
IMG_5006.HEIC
IMG_5007.HEIC
IMG_5008.HEIC
IMG_5009.HEIC
IMG_5010.HEIC
IMG_5012.HEIC
IMG_5013.HEIC
IMG_5014.HEIC
IMG_5015.HEIC
InterimStmt_20221230.pdf
Motherland_Fort_Salem_S03E01_480p_WEB-DL_RMTeam.mkv
OnlineTrade 2/
Real estate/
Sales Data.csv
Screen Shot 2022-10-03 at 6.47.46 AM.png
The.Lord.of.the.Rings.The.Rings.of.Power.S01E03.(NKIRI.COM).mkv
[Waploaded]_farming-2019.mp4
ad8cbe3e-aeb3-4dbc-9baa-120bced58b11.JPG
beam/
bill.pdf
bitcoin.jpeg
blog-details.html*
cf2dcd66-a2aa-4321-b11d-13d5e5011e9b.JPG
d562e97e-209f-44ae-99b8-972350ac766c.JPG
diabetes.csv
e0bb684a-4f2f-463a-b309-97eec0a0d33b.JPG
e46796bc-b52e-46d8-8e11-ccb238776bed.JPG
eae747ac-4183-45bd-82b1-27f525b3710b.JPG
eede4b83-4403-44a0-9420-5cd53afbcfff.JPG
faq.html*
favicon.ico
ff135690-c714-488c-9f90-1bcf1681b2b1.JPG
ffdade24-2654-4da4-ae91-3652dc149c1b.JPG
how-it-works.html*
image (1).jpg
image.jpg
logo-dark.png
logo.JPG
logo.png
privacy-policy.html*
service-details.html*
terms.html*
theme/
titanic.csv
wallpaperflare.com_wallpaper (1).jpg
‹ Fastlane Logistics — WordPress.pdf
In [8]:
cd

/Users/mac
In [9]:
cd documents

/Users/mac/Documents
In [10]:
ls

GitHub/                Nicepage/              WORDPRESS BTC/
My Tableau Repository/ Nicepage Templates/    archbb/
New/                   PlaybackEventStreams/  ikkuna-master/
New.zip                Sales Data.csv
In [11]:
df = pd.read_csv('Sales Data.csv')
In [12]:
df.head()
Out[12]:
Unnamed: 0 Order ID Product Quantity Ordered Price Each Order Date Purchase Address Month Sales City Hour
0 0 295665 Macbook Pro Laptop 1 1700.00 2019-12-30 00:01:00 136 Church St, New York City, NY 10001 12 1700.00 New York City 0
1 1 295666 LG Washing Machine 1 600.00 2019-12-29 07:03:00 562 2nd St, New York City, NY 10001 12 600.00 New York City 7
2 2 295667 USB-C Charging Cable 1 11.95 2019-12-12 18:21:00 277 Main St, New York City, NY 10001 12 11.95 New York City 18
3 3 295668 27in FHD Monitor 1 149.99 2019-12-22 15:13:00 410 6th St, San Francisco, CA 94016 12 149.99 San Francisco 15
4 4 295669 USB-C Charging Cable 1 11.95 2019-12-18 12:38:00 43 Hill St, Atlanta, GA 30301 12 11.95 Atlanta 12
In [13]:
df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 185950 entries, 0 to 185949
Data columns (total 11 columns):
 #   Column            Non-Null Count   Dtype  
---  ------            --------------   -----  
 0   Unnamed: 0        185950 non-null  int64  
 1   Order ID          185950 non-null  int64  
 2   Product           185950 non-null  object 
 3   Quantity Ordered  185950 non-null  int64  
 4   Price Each        185950 non-null  float64
 5   Order Date        185950 non-null  object 
 6   Purchase Address  185950 non-null  object 
 7   Month             185950 non-null  int64  
 8   Sales             185950 non-null  float64
 9   City              185950 non-null  object 
 10  Hour              185950 non-null  int64  
dtypes: float64(2), int64(5), object(4)
memory usage: 15.6+ MB
In [14]:
df.head()
Out[14]:
Unnamed: 0 Order ID Product Quantity Ordered Price Each Order Date Purchase Address Month Sales City Hour
0 0 295665 Macbook Pro Laptop 1 1700.00 2019-12-30 00:01:00 136 Church St, New York City, NY 10001 12 1700.00 New York City 0
1 1 295666 LG Washing Machine 1 600.00 2019-12-29 07:03:00 562 2nd St, New York City, NY 10001 12 600.00 New York City 7
2 2 295667 USB-C Charging Cable 1 11.95 2019-12-12 18:21:00 277 Main St, New York City, NY 10001 12 11.95 New York City 18
3 3 295668 27in FHD Monitor 1 149.99 2019-12-22 15:13:00 410 6th St, San Francisco, CA 94016 12 149.99 San Francisco 15
4 4 295669 USB-C Charging Cable 1 11.95 2019-12-18 12:38:00 43 Hill St, Atlanta, GA 30301 12 11.95 Atlanta 12
In [15]:
df.isnull().sum()
Out[15]:
Unnamed: 0          0
Order ID            0
Product             0
Quantity Ordered    0
Price Each          0
Order Date          0
Purchase Address    0
Month               0
Sales               0
City                0
Hour                0
dtype: int64
In [16]:
df =df.dropna(how='all')
df.shape
Out[16]:
(185950, 11)

what is the best month for sale?¶

In [17]:
'04/19/19 08.46'.split('/')[0]
Out[17]:
'04'
In [18]:
def Month(x):
    
    
    return x .split('/')[0]
In [19]:
df['Month'] = df ['Order Date']. apply(Month)
In [20]:
df.dtypes
Out[20]:
Unnamed: 0            int64
Order ID              int64
Product              object
Quantity Ordered      int64
Price Each          float64
Order Date           object
Purchase Address     object
Month                object
Sales               float64
City                 object
Hour                  int64
dtype: object
In [21]:
df['Month'].unique()
Out[21]:
array(['2019-12-30 00:01:00', '2019-12-29 07:03:00',
       '2019-12-12 18:21:00', ..., '2019-06-09 22:07:00',
       '2019-06-26 18:35:00', '2019-06-25 14:33:00'], dtype=object)
In [22]:
filter=df['Month']=='Order Date'
len (df[~filter])
Out[22]:
185950
In [23]:
df=df[~filter]
In [24]:
df.shape
Out[24]:
(185950, 11)
In [25]:
df.head()
Out[25]:
Unnamed: 0 Order ID Product Quantity Ordered Price Each Order Date Purchase Address Month Sales City Hour
0 0 295665 Macbook Pro Laptop 1 1700.00 2019-12-30 00:01:00 136 Church St, New York City, NY 10001 2019-12-30 00:01:00 1700.00 New York City 0
1 1 295666 LG Washing Machine 1 600.00 2019-12-29 07:03:00 562 2nd St, New York City, NY 10001 2019-12-29 07:03:00 600.00 New York City 7
2 2 295667 USB-C Charging Cable 1 11.95 2019-12-12 18:21:00 277 Main St, New York City, NY 10001 2019-12-12 18:21:00 11.95 New York City 18
3 3 295668 27in FHD Monitor 1 149.99 2019-12-22 15:13:00 410 6th St, San Francisco, CA 94016 2019-12-22 15:13:00 149.99 San Francisco 15
4 4 295669 USB-C Charging Cable 1 11.95 2019-12-18 12:38:00 43 Hill St, Atlanta, GA 30301 2019-12-18 12:38:00 11.95 Atlanta 12
In [26]:
df["Month"]
Out[26]:
0         2019-12-30 00:01:00
1         2019-12-29 07:03:00
2         2019-12-12 18:21:00
3         2019-12-22 15:13:00
4         2019-12-18 12:38:00
                 ...         
185945    2019-06-07 19:02:00
185946    2019-06-01 19:29:00
185947    2019-06-22 18:57:00
185948    2019-06-26 18:35:00
185949    2019-06-25 14:33:00
Name: Month, Length: 185950, dtype: object
In [27]:
df.dtypes
Out[27]:
Unnamed: 0            int64
Order ID              int64
Product              object
Quantity Ordered      int64
Price Each          float64
Order Date           object
Purchase Address     object
Month                object
Sales               float64
City                 object
Hour                  int64
dtype: object
In [28]:
df['Price Each']=df['Price Each'].astype(float)
In [29]:
df['Quantity Ordered']=df['Quantity Ordered'].astype(int)
In [30]:
df['sales']=df['Quantity Ordered']*df['Price Each']
df.head(5)
Out[30]:
Unnamed: 0 Order ID Product Quantity Ordered Price Each Order Date Purchase Address Month Sales City Hour sales
0 0 295665 Macbook Pro Laptop 1 1700.00 2019-12-30 00:01:00 136 Church St, New York City, NY 10001 2019-12-30 00:01:00 1700.00 New York City 0 1700.00
1 1 295666 LG Washing Machine 1 600.00 2019-12-29 07:03:00 562 2nd St, New York City, NY 10001 2019-12-29 07:03:00 600.00 New York City 7 600.00
2 2 295667 USB-C Charging Cable 1 11.95 2019-12-12 18:21:00 277 Main St, New York City, NY 10001 2019-12-12 18:21:00 11.95 New York City 18 11.95
3 3 295668 27in FHD Monitor 1 149.99 2019-12-22 15:13:00 410 6th St, San Francisco, CA 94016 2019-12-22 15:13:00 149.99 San Francisco 15 149.99
4 4 295669 USB-C Charging Cable 1 11.95 2019-12-18 12:38:00 43 Hill St, Atlanta, GA 30301 2019-12-18 12:38:00 11.95 Atlanta 12 11.95
In [31]:
df.groupby('Month')['sales'].sum()
Out[31]:
Month
2019-01-01 03:07:00     11.99
2019-01-01 03:40:00     11.95
2019-01-01 04:56:00    150.00
2019-01-01 05:53:00      2.99
2019-01-01 06:03:00     23.90
                        ...  
2020-01-01 04:06:00    149.99
2020-01-01 04:13:00      2.99
2020-01-01 04:21:00     11.95
2020-01-01 04:54:00     99.99
2020-01-01 05:13:00    114.94
Name: sales, Length: 142395, dtype: float64

which city has max order¶

In [32]:
'917 1st St,Dallas, TX75001'.split(',')[1]
Out[32]:
'Dallas'
In [33]:
def city(x):
    return x.split(',')[1]
In [34]:
df['city'] =df['Purchase Address'].apply(city)
In [35]:
df.groupby('city')['city'].count()
Out[35]:
city
 Atlanta          14881
 Austin            9905
 Boston           19934
 Dallas           14820
 Los Angeles      29605
 New York City    24876
 Portland         12465
 San Francisco    44732
 Seattle          14732
Name: city, dtype: int64
In [36]:
plt.bar(df.groupby('city')['city'].count().index,df.groupby('city')['city'].count())
plt.xticks(rotation='vertical')
plt.ylabel('received orders')
plt.xlabel('city names')
plt.show()

what time should we Display to maximise for product purchase¶

In [37]:
# df['Order Date'][0].dtype
In [38]:
df['Hour']=pd.to_datetime(df['Order Date']).dt.hour
In [39]:
keys = []
hour = []
for key,hour_df in df.groupby('Hour'):
    keys.append(key)
    hour.append(len(hour_df))
In [40]:
plt.grid()
plt.plot(keys,hour)
Out[40]:
[<matplotlib.lines.Line2D at 0x1503df4d0>]

between 12pm and 7pm is probably the best time to advertise to maxmimise product purchase , what product sold the most and why?¶

In [41]:
df.groupby('Product')['Quantity Ordered'].sum().plot(kind='bar')
Out[41]:
<Axes: xlabel='Product'>
In [42]:
df.groupby('Product')['Price Each'].mean()
Out[42]:
Product
20in Monitor                   109.99
27in 4K Gaming Monitor         389.99
27in FHD Monitor               149.99
34in Ultrawide Monitor         379.99
AA Batteries (4-pack)            3.84
AAA Batteries (4-pack)           2.99
Apple Airpods Headphones       150.00
Bose SoundSport Headphones      99.99
Flatscreen TV                  300.00
Google Phone                   600.00
LG Dryer                       600.00
LG Washing Machine             600.00
Lightning Charging Cable        14.95
Macbook Pro Laptop            1700.00
ThinkPad Laptop                999.99
USB-C Charging Cable            11.95
Vareebadd Phone                400.00
Wired Headphones                11.99
iPhone                         700.00
Name: Price Each, dtype: float64
In [43]:
products=df.groupby('Product')['Quantity Ordered'].sum().index
quantity=df.groupby('Product')['Quantity Ordered'].sum()
prices=df.groupby('Product')['Price Each'].mean()
In [44]:
plt.figure(figsize=(40,24))
fig,ax1=plt.subplots()
ax2=ax1.twinx()
ax1.bar(products,quantity,color='g')
ax2.plot(products,prices,'b-')
ax1.set_xticklabels(products,rotation='vertical',size=8)

/var/folders/7v/92s_wyw97qb555bhcykb9hvw0000gn/T/ipykernel_10498/3467980537.py:6: UserWarning:

FixedFormatter should only be used together with FixedLocator
Out[44]:
[Text(0, 0, '20in Monitor'),
 Text(1, 0, '27in 4K Gaming Monitor'),
 Text(2, 0, '27in FHD Monitor'),
 Text(3, 0, '34in Ultrawide Monitor'),
 Text(4, 0, 'AA Batteries (4-pack)'),
 Text(5, 0, 'AAA Batteries (4-pack)'),
 Text(6, 0, 'Apple Airpods Headphones'),
 Text(7, 0, 'Bose SoundSport Headphones'),
 Text(8, 0, 'Flatscreen TV'),
 Text(9, 0, 'Google Phone'),
 Text(10, 0, 'LG Dryer'),
 Text(11, 0, 'LG Washing Machine'),
 Text(12, 0, 'Lightning Charging Cable'),
 Text(13, 0, 'Macbook Pro Laptop'),
 Text(14, 0, 'ThinkPad Laptop'),
 Text(15, 0, 'USB-C Charging Cable'),
 Text(16, 0, 'Vareebadd Phone'),
 Text(17, 0, 'Wired Headphones'),
 Text(18, 0, 'iPhone')]
<Figure size 4000x2400 with 0 Axes>

The top selling product is 'AAA Batteries: The top selling products seem to have a correlation with the price of the product. The cheaper the product higher the quantity ordered and vice versa¶

What products are most often sold together? note: keep orders that have same order Id are sold mostly together

In [45]:
db=df[df['Order ID'].duplicated(keep=False)]
db.head(20)
Out[45]:
Unnamed: 0 Order ID Product Quantity Ordered Price Each Order Date Purchase Address Month Sales City Hour sales city
16 16 295681 Google Phone 1 600.00 2019-12-25 12:37:00 79 Elm St, Boston, MA 02215 2019-12-25 12:37:00 600.00 Boston 12 600.00 Boston
17 17 295681 USB-C Charging Cable 1 11.95 2019-12-25 12:37:00 79 Elm St, Boston, MA 02215 2019-12-25 12:37:00 11.95 Boston 12 11.95 Boston
18 18 295681 Bose SoundSport Headphones 1 99.99 2019-12-25 12:37:00 79 Elm St, Boston, MA 02215 2019-12-25 12:37:00 99.99 Boston 12 99.99 Boston
19 19 295681 Wired Headphones 1 11.99 2019-12-25 12:37:00 79 Elm St, Boston, MA 02215 2019-12-25 12:37:00 11.99 Boston 12 11.99 Boston
36 36 295698 Vareebadd Phone 1 400.00 2019-12-13 14:32:00 175 1st St, New York City, NY 10001 2019-12-13 14:32:00 400.00 New York City 14 400.00 New York City
37 37 295698 USB-C Charging Cable 2 11.95 2019-12-13 14:32:00 175 1st St, New York City, NY 10001 2019-12-13 14:32:00 23.90 New York City 14 23.90 New York City
42 42 295703 AA Batteries (4-pack) 1 3.84 2019-12-17 12:27:00 502 Jefferson St, Austin, TX 73301 2019-12-17 12:27:00 3.84 Austin 12 3.84 Austin
43 43 295703 Bose SoundSport Headphones 1 99.99 2019-12-17 12:27:00 502 Jefferson St, Austin, TX 73301 2019-12-17 12:27:00 99.99 Austin 12 99.99 Austin
66 66 295726 iPhone 1 700.00 2019-12-25 14:49:00 203 Lakeview St, Boston, MA 02215 2019-12-25 14:49:00 700.00 Boston 14 700.00 Boston
67 67 295726 Lightning Charging Cable 1 14.95 2019-12-25 14:49:00 203 Lakeview St, Boston, MA 02215 2019-12-25 14:49:00 14.95 Boston 14 14.95 Boston
76 76 295735 iPhone 1 700.00 2019-12-22 18:25:00 374 Lincoln St, New York City, NY 10001 2019-12-22 18:25:00 700.00 New York City 18 700.00 New York City
77 77 295735 Apple Airpods Headphones 1 150.00 2019-12-22 18:25:00 374 Lincoln St, New York City, NY 10001 2019-12-22 18:25:00 150.00 New York City 18 150.00 New York City
78 78 295735 Wired Headphones 1 11.99 2019-12-22 18:25:00 374 Lincoln St, New York City, NY 10001 2019-12-22 18:25:00 11.99 New York City 18 11.99 New York City
80 80 295737 iPhone 1 700.00 2019-12-19 08:51:00 966 10th St, Atlanta, GA 30301 2019-12-19 08:51:00 700.00 Atlanta 8 700.00 Atlanta
81 81 295737 Lightning Charging Cable 1 14.95 2019-12-19 08:51:00 966 10th St, Atlanta, GA 30301 2019-12-19 08:51:00 14.95 Atlanta 8 14.95 Atlanta
97 97 295753 34in Ultrawide Monitor 1 379.99 2019-12-25 06:26:00 365 Washington St, Dallas, TX 75001 2019-12-25 06:26:00 379.99 Dallas 6 379.99 Dallas
98 98 295753 Lightning Charging Cable 1 14.95 2019-12-25 06:26:00 365 Washington St, Dallas, TX 75001 2019-12-25 06:26:00 14.95 Dallas 6 14.95 Dallas
104 104 295759 Bose SoundSport Headphones 1 99.99 2019-12-25 06:53:00 15 Pine St, New York City, NY 10001 2019-12-25 06:53:00 99.99 New York City 6 99.99 New York City
105 105 295759 Wired Headphones 1 11.99 2019-12-25 06:53:00 15 Pine St, New York City, NY 10001 2019-12-25 06:53:00 11.99 New York City 6 11.99 New York City
129 129 295783 Vareebadd Phone 1 400.00 2019-12-06 12:41:00 87 5th St, San Francisco, CA 94016 2019-12-06 12:41:00 400.00 San Francisco 12 400.00 San Francisco
In [46]:
db['Grouped']=db.groupby('Order ID')['Product'].transform(lambda x: ','.join(x))

/var/folders/7v/92s_wyw97qb555bhcykb9hvw0000gn/T/ipykernel_10498/2681736227.py:1: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
In [47]:
#lets drop out all duplicates Order ID
db2=db.drop_duplicates(subset=['Order ID'])
In [48]:
db2['Grouped'].value_counts()[0:5].plot.pie()
Out[48]:
<Axes: ylabel='Grouped'>
In [49]:
values =db2['Grouped'].value_counts()[0:5]
labels=db['Grouped'].value_counts()[0:5].index
In [50]:
trace=go.Pie(labels=labels, values=values,
            hoverinfo='label+percent', textinfo='value',
            textfont=dict(size=25),
            pull=[0,0,0,0.2,0]
            )
In [ ]: