
# import os
# # os.environ['PATH'].split(';')


# Importing packages, set data source paths
import pandas as pd
import numpy as np

breast_cancer = 'https://raw.githubusercontent.com/datamites/pandas/master/breast_cancer.csv'
adult = 'https://raw.githubusercontent.com/datamites/pandas/master/adult10.data'
book_price = 'https://raw.githubusercontent.com/datamites/pandas/master/book_price_data.xlsx'
book_reviews = 'https://raw.githubusercontent.com/datamites/pandas/master/book_reviews_price.xlsx'
hp_costs = 'https://raw.githubusercontent.com/datamites/pandas/master/hp_other_costs.csv'
house_price_bangalore = 'https://raw.githubusercontent.com/datamites/pandas/master/house_price_bangalore.csv'
mtcars = 'https://raw.githubusercontent.com/datamites/pandas/master/mtcars.csv'
mtcars_missing = 'https://raw.githubusercontent.com/datamites/pandas/master/mtcars_missing.csv'
wine= 'https://raw.githubusercontent.com/datamites/pandas/master/winequality.csv'
sales_returns = 'https://raw.githubusercontent.com/datamites/pandas/master/sales_returns.csv'
superstore_orders = 'https://raw.githubusercontent.com/datamites/pandas/master/superstore_orders.csv'
car_sales = 'https://raw.githubusercontent.com/datamites/pandas/master/car-sales.csv'


import pandas as pd
import numpy as np


hp_costs = 'https://raw.githubusercontent.com/datamites/pandas/master/hp_other_costs.csv'


data = pd.read_csv(hp_costs)
print(data.shape)
data.head()

(13320, 10)


data.columns

Index(['area_type', 'availability', 'location', 'size', 'society',
       'total_sqft', 'bath', 'balcony', 'other_costs', 'price'],
      dtype='object')


data.other_costs[0]

'custom 2.0L reg 1.76L misc 3.7L'


data.other_costs.str.findall('\d+.\d+')

0              [2.0, 1.76, 3.7]
1                    [2.4, 5.4]
2                   [2.79, 3.5]
3        [2.5, 4.28, 1.34, 1.6]
4                         [2.3]
                  ...          
13315          [1.8, 10.4, 3.2]
13316                [4.1, 3.9]
13317           [5.6, 2.7, 2.4]
13318         [3.9, 21.96, 1.4]
13319          [3.0, 0.77, 1.9]
Name: other_costs, Length: 13320, dtype: object


data['other_costs_list'] = data.other_costs.str.findall('\d+.\d+')
data.head()


for i, row in data.iterrows():
    data.loc[i, 'total_cost'] = row.price + sum([float(x) for x in row.other_costs_list])


data.head()


superstore_orders = 'https://raw.githubusercontent.com/datamites/pandas/master/superstore_orders.csv'
data2 = pd.read_csv(superstore_orders)
print(data2.shape)
data2.head(5)

(9994, 21)


data2.columns

Index(['row_id', 'order_id', 'order_date', 'ship_date', 'ship_mode',
       'customer_id', 'customer_name', 'segment', 'country', 'city', 'state',
       'postal_code', 'region', 'product_id', 'category', 'sub_category',
       'product_name', 'sales', 'quantity', 'discount', 'profit'],
      dtype='object')


data2.pivot_table(columns='region', index='category', values='sales', aggfunc='sum')


data2.pivot_table(columns='region', index='category', values=['sales','profit'], aggfunc='sum')


data2.pivot_table(columns='region', index=['category','sub_category'], values=['sales','profit'], aggfunc='sum').style.background_gradient(cmap='coolwarm')


data3 = pd.read_csv(wine, delimiter=';')
print(data3.shape)
data3.head()

(4898, 12)


data3.quality.value_counts()

6    2198
5    1457
7     880
8     175
4     163
3      20
9       5
Name: quality, dtype: int64


# Create a new column quality_category

data3['quality_category'] = pd.cut(data3.quality, bins=[0,5,7,10], labels = ['bad', 'good', 'premium'])
data3.head(20)


data4 = pd.read_excel(book_reviews)
print(data4.shape)
data4.head()

(100, 8)


data4.Author.str.split(" ",n=1, expand=True)


data4['Author_Firstname'] = data4.Author.str.split(" ",n=1, expand=True)[0]
data4['Author_Lastname'] = data4.Author.str.split(" ",n=1, expand=True)[1]
data4.head()


data4.Reviews.str.split(" ", expand=True)


data4['Reviews_percent'] = data4.Reviews.str.split(" ", expand=True)[0].astype('float')/data4.Reviews.str.split(" ", expand=True)[3].astype('float')


data.head()


from scipy import stats

data5 = pd.read_csv(mtcars)
print(data5.shape)
data5.head()

(32, 12)


stats.zscore(data5.hp)   # just for one value

array([-0.54365487, -0.54365487, -0.7955699 , -0.54365487,  0.41954967,
       -0.61774753,  1.45684686, -1.25494437, -0.76593284, -0.35101396,
       -0.35101396,  0.49364233,  0.49364233,  0.49364233,  0.86410561,
        1.01229092,  1.23456889, -1.19567025, -1.40312969, -1.21048878,
       -0.73629578,  0.04908639,  0.04908639,  1.45684686,  0.41954967,
       -1.19567025, -0.82520696, -0.49919927,  1.73839896,  0.41954967,
        2.79051468, -0.5584734 ])


data5[abs(stats.zscore(data5.hp))<2.3]


data5[(abs(stats.zscore(data5.iloc[:,1:])<3)).all(axis=1)]   # abs = absolute value


# dropna = drop not available
data6 = pd.read_csv(mtcars_missing)
print(data6.shape)
data6.head()

(32, 12)


data6.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 32 entries, 0 to 31
Data columns (total 12 columns):
 #   Column     Non-Null Count  Dtype  
---  ------     --------------  -----  
 0   car_model  32 non-null     object 
 1   mpg        31 non-null     float64
 2   cyl        32 non-null     int64  
 3   disp       25 non-null     object 
 4   hp         30 non-null     float64
 5   drat       31 non-null     float64
 6   wt         28 non-null     object 
 7   qsec       20 non-null     object 
 8   vs         32 non-null     int64  
 9   am         32 non-null     int64  
 10  gear       32 non-null     int64  
 11  carb       32 non-null     int64  
dtypes: float64(3), int64(5), object(4)
memory usage: 3.1+ KB


#data6.disp.sort_values()


data6.replace(['$', '?', '*', '-'],np.nan, inplace=True)


data6.head()


data6.isnull().sum()

car_model     0
mpg           1
cyl           0
disp          9
hp            2
drat          1
wt            6
qsec         14
vs            0
am            0
gear          0
carb          0
dtype: int64


data6.isnull().sum().sum()

33


# data6.dropna(how='all')
# data6.dropna(how='any')


len(data6)*0.6

19.2


data6.dropna(thresh=len(data6)*0.6, axis=1)


data7 = pd.read_csv(house_price_bangalore)
print(data7.shape)
data7.head()

(13320, 9)


from sklearn.preprocessing import LabelEncoder


data7.loc[:,['area_type', 'location', 'society']]


data7.fillna(method='ffill',inplace=True)


data7.loc[:,['area_type', 'location', 'society']].apply(LabelEncoder().fit_transform)


data7.loc[:,['area_type', 'location', 'society']] = data7.loc[:,['area_type', 'location', 'society']].apply(LabelEncoder().fit_transform)


data7.head()


data8= pd.read_csv(breast_cancer)
print(data8.shape)
data8.head()

(569, 31)


pd.set_option('display.max_columns', 50)


data8.head()


# pd.set_option? VIP


data9 = pd.read_csv(superstore_orders)
print(data9.shape)
data9.head()

(9994, 21)


data9 = pd.read_csv(superstore_orders, parse_dates=['order_date','ship_date'])
print(data9.shape)
data9.head()

(9994, 21)


data9.order_date[0]

Timestamp('2017-11-08 00:00:00')


data9.order_date[0].month

11


data.order_date[0].year

2017


data9['orderyear'] = data9.order_date.apply(lambda x: x.year)
data9['ordermonth'] = data9.order_date.apply(lambda x: x.month)
data9.head()


data9.pivot_table(columns='orderyear',index='category', values='sales', aggfunc='sum').style.background_gradient(cmap='coolwarm')


data9.pivot_table(columns='orderyear',index='category', values='sales', aggfunc='sum').pct_change(axis=1)*100


data9.pivot_table(columns='orderyear',index='category', values='profit', aggfunc='sum').pct_change(axis=1)*100


data11 = pd.read_csv(breast_cancer)
data11.head()


data11.corr().style.background_gradient('coolwarm')
# data11.corr().style.background_gradient('twilight')


data12 = pd.read_csv(superstore_orders)
data12.head()


data12 = pd.read_csv(superstore_orders, dtype= {'postal_code':'str'})
data12.head()


data12.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 9994 entries, 0 to 9993
Data columns (total 21 columns):
 #   Column         Non-Null Count  Dtype  
---  ------         --------------  -----  
 0   row_id         9994 non-null   int64  
 1   order_id       9994 non-null   object 
 2   order_date     9994 non-null   object 
 3   ship_date      9994 non-null   object 
 4   ship_mode      9994 non-null   object 
 5   customer_id    9994 non-null   object 
 6   customer_name  9994 non-null   object 
 7   segment        9994 non-null   object 
 8   country        9994 non-null   object 
 9   city           9994 non-null   object 
 10  state          9994 non-null   object 
 11  postal_code    9983 non-null   object 
 12  region         9994 non-null   object 
 13  product_id     9994 non-null   object 
 14  category       9994 non-null   object 
 15  sub_category   9994 non-null   object 
 16  product_name   9994 non-null   object 
 17  sales          9994 non-null   float64
 18  quantity       9994 non-null   int64  
 19  discount       9994 non-null   float64
 20  profit         9994 non-null   float64
dtypes: float64(3), int64(2), object(16)
memory usage: 1.6+ MB


data13 = pd.read_csv(car_sales)
data13.head()


data13 = pd.read_csv(car_sales,index_col='Month',parse_dates=['Month'])
data13.head()


data13.plot();


data14 = pd.read_csv(adult)
data14.head()


data = pd.read_csv(adult, usecols=['age','workclass','education','race'])
data.head()


data15 = pd.read_csv(mtcars_missing)
data15.head()


data15.replace(['$','*','-','?'], np.nan, inplace=True)
data15.head()


data15.isnull().sum()

33


data15.shape

(32, 12)


(data15.shape[0]-data15.dropna().shape[0])*100/data15.shape[0]

65.625


data16 = pd.read_csv('log-15feb18.txt')
print(data16.shape)
data16.head()

(20, 4)


from glob import glob
glob('*')

['00 Top 40 des astuces utiles pandas Partie 1.ipynb',
 'adult10.data',
 'book_price_data.xlsx',
 'book_reviews_price.xlsx',
 'breast_cancer.csv',
 'car-sales.csv',
 'house_price_bangalore.csv',
 'hp_other_costs.csv',
 'log-15feb18.txt',
 'log-16feb18.txt',
 'log-17feb18.txt',
 'log-18feb18.txt',
 'log-19feb18.txt',
 'mtcars.csv',
 'mtcars_missing.csv',
 'Pandas Tutorial - Top 40 Useful Tricks.ipynb',
 'sales_returns.csv',
 'superstore_orders.csv',
 'winequality.csv']


glob('log*')

['log-15feb18.txt',
 'log-16feb18.txt',
 'log-17feb18.txt',
 'log-18feb18.txt',
 'log-19feb18.txt']


files = glob('log*')
files.sort()
files

['log-15feb18.txt',
 'log-16feb18.txt',
 'log-17feb18.txt',
 'log-18feb18.txt',
 'log-19feb18.txt']


data16 = pd.concat( (pd.read_csv(file) for file in files), ignore_index=True)
data16.head(25)


data16.shape

(184, 4)


data17 = pd.read_csv(adult)
data17.head()


data17.select_dtypes(include='object')


data18 = pd.concat((data17.select_dtypes(include='object'),data17.select_dtypes(exclude='object')),axis=1)


data18.head()


from sklearn.preprocessing import LabelEncoder
data18.loc[:, 'workclass':'category'] = data18.loc[:, 'workclass':'category'].apply(LabelEncoder().fit_transform)


data18.head()


data19 = pd.read_csv(breast_cancer)
print(data19.shape)
data19.head()

(569, 31)


data_corr = data19.corr()


data_corr.outcome*100

mean radius                 73.002851
mean texture                41.518530
mean perimeter              74.263553
mean area                   70.898384
mean smoothness             35.855997
mean compactness            59.653368
mean concavity              69.635971
mean concave points         77.661384
mean symmetry               33.049855
mean fractal dimension      -1.283760
radius error                56.713382
texture error               -0.830333
perimeter error             55.614070
area error                  54.823594
smoothness error            -6.701601
compactness error           29.299924
concavity error             25.372977
concave points error        40.804233
symmetry error              -0.652176
fractal dimension error      7.797242
worst radius                77.645378
worst texture               45.690282
worst perimeter             78.291414
worst area                  73.382503
worst smoothness            42.146486
worst compactness           59.099824
worst concavity             65.961021
worst concave points        79.356602
worst symmetry              41.629431
worst fractal dimension     32.387219
outcome                    100.000000
Name: outcome, dtype: float64


data_corr.outcome.sort_values(ascending=False)

outcome                    1.000000
worst concave points       0.793566
worst perimeter            0.782914
mean concave points        0.776614
worst radius               0.776454
mean perimeter             0.742636
worst area                 0.733825
mean radius                0.730029
mean area                  0.708984
mean concavity             0.696360
worst concavity            0.659610
mean compactness           0.596534
worst compactness          0.590998
radius error               0.567134
perimeter error            0.556141
area error                 0.548236
worst texture              0.456903
worst smoothness           0.421465
worst symmetry             0.416294
mean texture               0.415185
concave points error       0.408042
mean smoothness            0.358560
mean symmetry              0.330499
worst fractal dimension    0.323872
compactness error          0.292999
concavity error            0.253730
fractal dimension error    0.077972
symmetry error            -0.006522
texture error             -0.008303
mean fractal dimension    -0.012838
smoothness error          -0.067016
Name: outcome, dtype: float64


data20 = pd.read_csv(breast_cancer)
print(data20.shape)
data20.head()

(569, 31)


data20.rename(columns = {'mean radius': 'rayon moyen'},inplace=True)


data20.head()


data20.columns.str.replace( ' ','_')

Index(['rayon_moyen', 'mean_texture', 'mean_perimeter', 'mean_area',
       'mean_smoothness', 'mean_compactness', 'mean_concavity',
       'mean_concave_points', 'mean_symmetry', 'mean_fractal_dimension',
       'radius_error', 'texture_error', 'perimeter_error', 'area_error',
       'smoothness_error', 'compactness_error', 'concavity_error',
       'concave_points_error', 'symmetry_error', 'fractal_dimension_error',
       'worst_radius', 'worst_texture', 'worst_perimeter', 'worst_area',
       'worst_smoothness', 'worst_compactness', 'worst_concavity',
       'worst_concave_points', 'worst_symmetry', 'worst_fractal_dimension',
       'outcome'],
      dtype='object')


data20.columns = data20.columns.str.replace('\W+',"_")

C:\Users\Pb\anaconda3\envs\Franckeale04\lib\site-packages\ipykernel_launcher.py:1: FutureWarning: The default value of regex will change from True to False in a future version.
  """Entry point for launching an IPython kernel.


data20.head()


data20.radius_error

0      1.0950
1      0.5435
2      0.7456
3      0.4956
4      0.7572
        ...  
564    1.1760
565    0.7655
566    0.4564
567    0.7260
568    0.3857
Name: radius_error, Length: 569, dtype: float64


# !{sys.executable} -m pip install pandas-profiling


import sys
import pandas_profiling
pandas_profiling.ProfileReport(mtcars)

	area_type	availability	location	size	society	total_sqft	bath	balcony	other_costs	price
0	Super built-up Area	19-Dec	Electronic City Phase II	2 BHK	Coomee	1056	2.0	1.0	custom 2.0L reg 1.76L misc 3.7L	39.07
1	Plot Area	Ready To Move	Chikka Tirupathi	4 Bedroom	Theanmp	2600	5.0	3.0	custom 2.4L reg 5.4L	120.00
2	Built-up Area	Ready To Move	Uttarahalli	3 BHK	NaN	1440	2.0	3.0	reg 2.79L misc 3.5L	62.00
3	Super built-up Area	Ready To Move	Lingadheeranahalli	3 BHK	Soiewre	1521	3.0	1.0	custom 2.5L reg 4.28L pd 1.34L misc 1.6L	95.00
4	Super built-up Area	Ready To Move	Kothanur	2 BHK	NaN	1200	2.0	1.0	reg 2.3L	51.00

	area_type	availability	location	size	society	total_sqft	bath	balcony	other_costs	price	other_costs_list
0	Super built-up Area	19-Dec	Electronic City Phase II	2 BHK	Coomee	1056	2.0	1.0	custom 2.0L reg 1.76L misc 3.7L	39.07	[2.0, 1.76, 3.7]
1	Plot Area	Ready To Move	Chikka Tirupathi	4 Bedroom	Theanmp	2600	5.0	3.0	custom 2.4L reg 5.4L	120.00	[2.4, 5.4]
2	Built-up Area	Ready To Move	Uttarahalli	3 BHK	NaN	1440	2.0	3.0	reg 2.79L misc 3.5L	62.00	[2.79, 3.5]
3	Super built-up Area	Ready To Move	Lingadheeranahalli	3 BHK	Soiewre	1521	3.0	1.0	custom 2.5L reg 4.28L pd 1.34L misc 1.6L	95.00	[2.5, 4.28, 1.34, 1.6]
4	Super built-up Area	Ready To Move	Kothanur	2 BHK	NaN	1200	2.0	1.0	reg 2.3L	51.00	[2.3]

	area_type	availability	location	size	society	total_sqft	bath	balcony	other_costs	price	other_costs_list	total_cost
0	Super built-up Area	19-Dec	Electronic City Phase II	2 BHK	Coomee	1056	2.0	1.0	custom 2.0L reg 1.76L misc 3.7L	39.07	[2.0, 1.76, 3.7]	46.53
1	Plot Area	Ready To Move	Chikka Tirupathi	4 Bedroom	Theanmp	2600	5.0	3.0	custom 2.4L reg 5.4L	120.00	[2.4, 5.4]	127.80
2	Built-up Area	Ready To Move	Uttarahalli	3 BHK	NaN	1440	2.0	3.0	reg 2.79L misc 3.5L	62.00	[2.79, 3.5]	68.29
3	Super built-up Area	Ready To Move	Lingadheeranahalli	3 BHK	Soiewre	1521	3.0	1.0	custom 2.5L reg 4.28L pd 1.34L misc 1.6L	95.00	[2.5, 4.28, 1.34, 1.6]	104.72
4	Super built-up Area	Ready To Move	Kothanur	2 BHK	NaN	1200	2.0	1.0	reg 2.3L	51.00	[2.3]	53.30

	row_id	order_id	order_date	ship_date	ship_mode	customer_id	customer_name	segment	country	city	...	postal_code	region	product_id	category	sub_category	product_name	sales	quantity	discount	profit
0	1	CA-2017-152156	2017-11-08	2017-11-11	Second Class	CG-12520	Claire Gute	Consumer	United States	Henderson	...	42420.0	South	FUR-BO-10001798	Furniture	Bookcases	Bush Somerset Collection Bookcase	261.9600	2	0.00	41.9136
1	2	CA-2017-152156	2017-11-08	2017-11-11	Second Class	CG-12520	Claire Gute	Consumer	United States	Henderson	...	42420.0	South	FUR-CH-10000454	Furniture	Chairs	Hon Deluxe Fabric Upholstered Stacking Chairs,...	731.9400	3	0.00	219.5820
2	3	CA-2017-138688	2017-06-12	2017-06-16	Second Class	DV-13045	Darrin Van Huff	Corporate	United States	Los Angeles	...	90036.0	West	OFF-LA-10000240	Office Supplies	Labels	Self-Adhesive Address Labels for Typewriters b...	14.6200	2	0.00	6.8714
3	4	US-2016-108966	2016-10-11	2016-10-18	Standard Class	SO-20335	Sean O'Donnell	Consumer	United States	Fort Lauderdale	...	33311.0	South	FUR-TA-10000577	Furniture	Tables	Bretford CR4500 Series Slim Rectangular Table	957.5775	5	0.45	-383.0310
4	5	US-2016-108966	2016-10-11	2016-10-18	Standard Class	SO-20335	Sean O'Donnell	Consumer	United States	Fort Lauderdale	...	33311.0	South	OFF-ST-10000760	Office Supplies	Storage	Eldon Fold 'N Roll Cart System	22.3680	2	0.20	2.5164

region	Central	East	South	West
category
Furniture	163797.1638	208291.204	117298.684	252612.7435
Office Supplies	167026.4150	205516.055	125651.313	220853.2490
Technology	170416.3120	264973.981	148771.908	251991.8320

PART - 1 (1 to 10)¶

1. Extracting data with Regular Expression¶

2. Pandas Pivot Table¶

Adding color Styling¶

3. Pandas cut method, continuous to categorical data¶

Classify Wine Quality (bad wine, good wine and premium wine)¶

4. Split strings to columns, expand¶

Add 2 more Columns `Author_Firstname` and `Author_Lastname`¶

Creer une nouvelle colonne de Reviews en %¶

5. Remove Outliers by Filtering¶

Suppression des valeurs aberrantes par filtrage¶

z value for entire data5¶

6. Handle missing values with dropna()¶

Checking the missing values¶

Supprimer tous NaN > 60% en utilisant `thresh`¶

7. Pandas Apply Function¶

Etant donner que nous avons de valeur manquantes, nous devons utiliser la méthode suivante:¶

8. Pandas set_option for formating, change default max_columns¶

Nous voulons voir toutes les colonne sans les (...)¶

9. Extracting Month & Year as separate columns from Pandas Date column¶

10. Percentage change function in Pandas DataFrame.¶

Python Pandas Tutorial: Top 40 Useful Tricks Part-2¶

11. Correlation Matrix Plot Pandas DataFrame¶

12. Import number column as string¶

13. Read date column from data as Index in DataFrame.¶

14. Read data only specific columns¶

15. Find percentage of records with missing values¶

16. Reading Multiple Files¶

17. Rearrange Numerical and Categorical Columns¶

18. Label encoding multiple columns¶

19. Finding correllation b/w features and target variable¶

20. Replace special chars in column names with '_' VIP¶

To remove all the special caracters¶

My top 25 pandas tricks¶

	fixed-acidity	volatile-acidity	citric acid	residual sugar	chlorides	free sulfur dioxide	total sulfur dioxide	density	pH	sulphates	alcohol	quality
0	7.0	0.27	0.36	20.7	0.045	45.0	170.0	1.0010	3.00	0.45	8.8	6
1	6.3	0.30	0.34	1.6	0.049	14.0	132.0	0.9940	3.30	0.49	9.5	6
2	8.1	0.28	0.40	6.9	0.050	30.0	97.0	0.9951	3.26	0.44	10.1	6
3	7.2	0.23	0.32	8.5	0.058	47.0	186.0	0.9956	3.19	0.40	9.9	6
4	7.2	0.23	0.32	8.5	0.058	47.0	186.0	0.9956	3.19	0.40	9.9	6

	fixed-acidity	volatile-acidity	citric acid	residual sugar	chlorides	free sulfur dioxide	total sulfur dioxide	density	pH	sulphates	alcohol	quality	quality_category
0	7.0	0.27	0.36	20.70	0.045	45.0	170.0	1.0010	3.00	0.45	8.8	6	good
1	6.3	0.30	0.34	1.60	0.049	14.0	132.0	0.9940	3.30	0.49	9.5	6	good
2	8.1	0.28	0.40	6.90	0.050	30.0	97.0	0.9951	3.26	0.44	10.1	6	good
3	7.2	0.23	0.32	8.50	0.058	47.0	186.0	0.9956	3.19	0.40	9.9	6	good
4	7.2	0.23	0.32	8.50	0.058	47.0	186.0	0.9956	3.19	0.40	9.9	6	good
5	8.1	0.28	0.40	6.90	0.050	30.0	97.0	0.9951	3.26	0.44	10.1	6	good
6	6.2	0.32	0.16	7.00	0.045	30.0	136.0	0.9949	3.18	0.47	9.6	6	good
7	7.0	0.27	0.36	20.70	0.045	45.0	170.0	1.0010	3.00	0.45	8.8	6	good
8	6.3	0.30	0.34	1.60	0.049	14.0	132.0	0.9940	3.30	0.49	9.5	6	good
9	8.1	0.22	0.43	1.50	0.044	28.0	129.0	0.9938	3.22	0.45	11.0	6	good
10	8.1	0.27	0.41	1.45	0.033	11.0	63.0	0.9908	2.99	0.56	12.0	5	bad
11	8.6	0.23	0.40	4.20	0.035	17.0	109.0	0.9947	3.14	0.53	9.7	5	bad
12	7.9	0.18	0.37	1.20	0.040	16.0	75.0	0.9920	3.18	0.63	10.8	5	bad
13	6.6	0.16	0.40	1.50	0.044	48.0	143.0	0.9912	3.54	0.52	12.4	7	good
14	8.3	0.42	0.62	19.25	0.040	41.0	172.0	1.0002	2.98	0.67	9.7	5	bad
15	6.6	0.17	0.38	1.50	0.032	28.0	112.0	0.9914	3.25	0.55	11.4	7	good
16	6.3	0.48	0.04	1.10	0.046	30.0	99.0	0.9928	3.24	0.36	9.6	6	good
17	6.2	0.66	0.48	1.20	0.029	29.0	75.0	0.9892	3.33	0.39	12.8	8	premium
18	7.4	0.34	0.42	1.10	0.033	17.0	171.0	0.9917	3.12	0.53	11.3	6	good
19	6.5	0.31	0.14	7.50	0.044	34.0	133.0	0.9955	3.22	0.50	9.5	5	bad

	Title	Author	Reviews	Ratings	Synopsis	Genre	BookCategory	Price
0	The Prisoner's Gold (The Hunters 3)	Chris Kuzneski	4.0 out of 5 stars	8 customer reviews	THE HUNTERS return in their third brilliant no...	Action & Adventure (Books)	Action & Adventure	220.00
1	Guru Dutt: A Tragedy in Three Acts	Arun Khopkar	3.9 out of 5 stars	14 customer reviews	A layered portrait of a troubled genius for wh...	Cinema & Broadcast (Books)	Biographies, Diaries & True Accounts	202.93
2	Leviathan (Penguin Classics)	Thomas Hobbes	9.6 out of 10 stars	6 customer reviews	"During the time men live without a common Pow...	International Relations	Humour	299.00
3	A Pocket Full of Rye (Miss Marple)	Agatha Christie	8.2 out of 10 stars	13 customer reviews	A handful of grain is found in the pocket of a...	Contemporary Fiction (Books)	Crime, Thriller & Mystery	180.00
4	ChiRunning: A Revolutionary Approach to Effort...	Danny Dreyer	4.5 out of 5 stars	8 customer reviews	The revised edition of the bestselling ChiRunn...	Healthy Living & Wellness (Books)	Sports	900.00

	0	1
0	Chris	Kuzneski
1	Arun	Khopkar
2	Thomas	Hobbes
3	Agatha	Christie
4	Danny	Dreyer
...	...	...
95	Ruskin	Bond
96	William	Tomkins
97	Leander	Kahney
98	Susan	Sontag
99	Agrawal	P.K

	0	1	2	3	4
0	4.0	out	of	5	stars
1	3.9	out	of	5	stars
2	9.6	out	of	10	stars
3	8.2	out	of	10	stars
4	4.5	out	of	5	stars
...	...	...	...	...	...
95	5.0	out	of	5	stars
96	4.0	out	of	5	stars
97	3.5	out	of	5	stars
98	4.5	out	of	5	stars
99	5.0	out	of	5	stars

	car_model	mpg	cyl	disp	hp	drat	wt	qsec	vs	am	gear	carb
0	Mazda RX4	21.0	6	160.0	110	3.90	2.620	16.46	0	1	4	4
1	Mazda RX4 Wag	21.0	6	160.0	110	3.90	2.875	17.02	0	1	4	4
2	Datsun 710	22.8	4	108.0	93	3.85	2.320	18.61	1	1	4	1
3	Hornet 4 Drive	21.4	6	258.0	110	3.08	3.215	19.44	1	0	3	1
4	Hornet Sportabout	18.7	8	360.0	175	3.15	3.440	17.02	0	0	3	2

	car_model	mpg	cyl	disp	hp	drat	wt	qsec	vs	am	gear	carb
0	Mazda RX4	21.0	6	160	110.0	3.90	2.62	16.46	0	1	4	4
1	Mazda RX4 Wag	21.0	6	$	110.0	NaN	2.875	*	0	1	4	4
2	Datsun 710	NaN	4	108	NaN	3.85	?	18.61	1	1	4	1
3	Hornet 4 Drive	999.0	6	NaN	NaN	3.08	3.215	-	1	0	3	1
4	Datsun 710	22.8	4	NaN	93.0	3.85	2.32	18.61	1	1	4	1

	area_type	location	society
0	3	419	464
1	2	317	2439
2	0	1179	2439
3	3	757	2186
4	3	716	2186
...	...	...	...
13315	0	1252	209
13316	3	1004	209
13317	0	972	1216
13318	3	907	2205
13319	3	396	2205

	mean radius	mean texture	mean perimeter	mean area	mean smoothness	mean compactness	mean concavity	mean concave points	mean symmetry	mean fractal dimension	...	worst texture	worst perimeter	worst area	worst smoothness	worst compactness	worst concavity	worst concave points	worst symmetry	worst fractal dimension	outcome
0	17.99	10.38	122.80	1001.0	0.11840	0.27760	0.3001	0.14710	0.2419	0.07871	...	17.33	184.60	2019.0	0.1622	0.6656	0.7119	0.2654	0.4601	0.11890	1
1	20.57	17.77	132.90	1326.0	0.08474	0.07864	0.0869	0.07017	0.1812	0.05667	...	23.41	158.80	1956.0	0.1238	0.1866	0.2416	0.1860	0.2750	0.08902	1
2	19.69	21.25	130.00	1203.0	0.10960	0.15990	0.1974	0.12790	0.2069	0.05999	...	25.53	152.50	1709.0	0.1444	0.4245	0.4504	0.2430	0.3613	0.08758	1
3	11.42	20.38	77.58	386.1	0.14250	0.28390	0.2414	0.10520	0.2597	0.09744	...	26.50	98.87	567.7	0.2098	0.8663	0.6869	0.2575	0.6638	0.17300	1
4	20.29	14.34	135.10	1297.0	0.10030	0.13280	0.1980	0.10430	0.1809	0.05883	...	16.67	152.20	1575.0	0.1374	0.2050	0.4000	0.1625	0.2364	0.07678	1

orderyear	2015	2016	2017	2018
category
Furniture	157192.853100	170518.237000	198901.436000	215387.269200
Office Supplies	151776.412000	137233.463000	183939.982000	246097.175000
Technology	175278.233000	162780.809000	226364.180000	271730.811000

		profit				sales
	region	Central	East	South	West	Central	East	South	West
category	sub_category
Furniture	Bookcases	-1997.904300	-1167.631800	1339.491800	-1646.511700	24157.176800	43819.334000	10899.362000	36004.123500
	Chairs	6592.722100	9357.770600	6612.089300	4027.584300	85230.646000	96260.683000	45176.446000	101781.328000
	Furnishings	-3906.216800	5881.407100	3442.682900	7641.270400	15254.370000	29071.380000	17306.684000	30072.730000
	Tables	-3559.650400	-11025.380100	-4623.057900	1482.607300	39154.971000	39139.807000	43916.192000	84754.562000
Office Supplies	Appliances	-2638.617500	8391.413400	4123.939600	8261.269900	23582.033000	34188.466000	19525.326000	30236.336000
	Art	1195.159100	1899.944300	1058.586600	2374.097000	5765.340000	7485.764000	4655.622000	9212.066000
	Binders	-1043.636900	11267.934600	3900.664000	16096.801600	56923.282000	53497.997000	37030.341000	55961.113000
	Envelopes	1777.528300	1812.409000	1465.477000	1908.762400	4636.872000	4375.874000	3345.556000	4118.100000
	Fasteners	236.618600	263.990800	173.718100	275.190700	778.030000	819.718000	503.316000	923.216000
	Labels	1073.079400	1129.280000	1040.772300	2303.122300	2451.472000	2602.934000	2353.180000	5078.726000
	Paper	6971.900500	9015.371000	5947.061400	12119.236400	17491.902000	20172.602000	14150.984000	26663.718000
	Storage	1969.836500	8389.371200	2274.296500	8645.322200	45930.112000	71612.584000	35768.060000	70532.852000
	Supplies	-661.888100	-1155.135200	1.877300	626.046500	9467.372000	10760.116000	8318.928000	18127.122000
Technology	Accessories	7251.630600	11195.864400	7004.542400	16484.598300	33956.076000	45033.372000	27276.754000	61114.116000
	Copiers	15608.841300	17022.841800	3658.906700	19327.235100	37259.570000	53219.462000	9299.756000	49749.242000
	Machines	-1486.066600	6928.642900	-1438.893000	-618.926400	26797.384000	66106.165000	53890.960000	42444.122000
	Phones	12323.026700	12314.686000	10767.275300	9110.742600	72403.282000	100614.982000	58304.438000	98684.352000

	car_model	mpg	cyl	disp	hp	drat	wt	qsec	vs	am	gear	carb
0	Mazda RX4	21.0	6	160.0	110	3.90	2.620	16.46	0	1	4	4
1	Mazda RX4 Wag	21.0	6	160.0	110	3.90	2.875	17.02	0	1	4	4
2	Datsun 710	22.8	4	108.0	93	3.85	2.320	18.61	1	1	4	1
3	Hornet 4 Drive	21.4	6	258.0	110	3.08	3.215	19.44	1	0	3	1
4	Hornet Sportabout	18.7	8	360.0	175	3.15	3.440	17.02	0	0	3	2
5	Valiant	18.1	6	225.0	105	2.76	3.460	20.22	1	0	3	1
6	Duster 360	14.3	8	360.0	245	3.21	3.570	15.84	0	0	3	4
7	Merc 240D	24.4	4	146.7	62	3.69	3.190	20.00	1	0	4	2
8	Merc 230	22.8	4	140.8	95	3.92	3.150	22.90	1	0	4	2
9	Merc 280	19.2	6	167.6	123	3.92	3.440	18.30	1	0	4	4
10	Merc 280C	17.8	6	167.6	123	3.92	3.440	18.90	1	0	4	4
11	Merc 450SE	16.4	8	275.8	180	3.07	4.070	17.40	0	0	3	3
12	Merc 450SL	17.3	8	275.8	180	3.07	3.730	17.60	0	0	3	3
13	Merc 450SLC	15.2	8	275.8	180	3.07	3.780	18.00	0	0	3	3
14	Cadillac Fleetwood	10.4	8	472.0	205	2.93	5.250	17.98	0	0	3	4
15	Lincoln Continental	10.4	8	460.0	215	3.00	5.424	17.82	0	0	3	4
16	Chrysler Imperial	14.7	8	440.0	230	3.23	5.345	17.42	0	0	3	4
17	Fiat 128	32.4	4	78.7	66	4.08	2.200	19.47	1	1	4	1
18	Honda Civic	30.4	4	75.7	52	4.93	1.615	18.52	1	1	4	2
19	Toyota Corolla	33.9	4	71.1	65	4.22	1.835	19.90	1	1	4	1
20	Toyota Corona	21.5	4	120.1	97	3.70	2.465	20.01	1	0	3	1
21	Dodge Challenger	15.5	8	318.0	150	2.76	3.520	16.87	0	0	3	2
22	AMC Javelin	15.2	8	304.0	150	3.15	3.435	17.30	0	0	3	2
23	Camaro Z28	13.3	8	350.0	245	3.73	3.840	15.41	0	0	3	4
24	Pontiac Firebird	19.2	8	400.0	175	3.08	3.845	17.05	0	0	3	2
25	Fiat X1-9	27.3	4	79.0	66	4.08	1.935	18.90	1	1	4	1
26	Porsche 914-2	26.0	4	120.3	91	4.43	2.140	16.70	0	1	5	2
27	Lotus Europa	30.4	4	95.1	113	3.77	1.513	16.90	1	1	5	2
28	Ford Pantera L	15.8	8	351.0	264	4.22	3.170	14.50	0	1	5	4
29	Ferrari Dino	19.7	6	145.0	175	3.62	2.770	15.50	0	1	5	6
31	Volvo 142E	21.4	4	121.0	109	4.11	2.780	18.60	1	1	4	2

	car_model	mpg	cyl	disp	hp	drat	wt	qsec	vs	am	gear	carb
0	Mazda RX4	21.0	6	160.0	110	3.90	2.620	16.46	0	1	4	4
1	Mazda RX4 Wag	21.0	6	160.0	110	3.90	2.875	17.02	0	1	4	4
2	Datsun 710	22.8	4	108.0	93	3.85	2.320	18.61	1	1	4	1
3	Hornet 4 Drive	21.4	6	258.0	110	3.08	3.215	19.44	1	0	3	1
4	Hornet Sportabout	18.7	8	360.0	175	3.15	3.440	17.02	0	0	3	2
5	Valiant	18.1	6	225.0	105	2.76	3.460	20.22	1	0	3	1
6	Duster 360	14.3	8	360.0	245	3.21	3.570	15.84	0	0	3	4
7	Merc 240D	24.4	4	146.7	62	3.69	3.190	20.00	1	0	4	2
8	Merc 230	22.8	4	140.8	95	3.92	3.150	22.90	1	0	4	2
9	Merc 280	19.2	6	167.6	123	3.92	3.440	18.30	1	0	4	4
10	Merc 280C	17.8	6	167.6	123	3.92	3.440	18.90	1	0	4	4
11	Merc 450SE	16.4	8	275.8	180	3.07	4.070	17.40	0	0	3	3
12	Merc 450SL	17.3	8	275.8	180	3.07	3.730	17.60	0	0	3	3
13	Merc 450SLC	15.2	8	275.8	180	3.07	3.780	18.00	0	0	3	3
14	Cadillac Fleetwood	10.4	8	472.0	205	2.93	5.250	17.98	0	0	3	4
15	Lincoln Continental	10.4	8	460.0	215	3.00	5.424	17.82	0	0	3	4
16	Chrysler Imperial	14.7	8	440.0	230	3.23	5.345	17.42	0	0	3	4
17	Fiat 128	32.4	4	78.7	66	4.08	2.200	19.47	1	1	4	1
18	Honda Civic	30.4	4	75.7	52	4.93	1.615	18.52	1	1	4	2
19	Toyota Corolla	33.9	4	71.1	65	4.22	1.835	19.90	1	1	4	1
20	Toyota Corona	21.5	4	120.1	97	3.70	2.465	20.01	1	0	3	1
21	Dodge Challenger	15.5	8	318.0	150	2.76	3.520	16.87	0	0	3	2
22	AMC Javelin	15.2	8	304.0	150	3.15	3.435	17.30	0	0	3	2
23	Camaro Z28	13.3	8	350.0	245	3.73	3.840	15.41	0	0	3	4
24	Pontiac Firebird	19.2	8	400.0	175	3.08	3.845	17.05	0	0	3	2
25	Fiat X1-9	27.3	4	79.0	66	4.08	1.935	18.90	1	1	4	1
26	Porsche 914-2	26.0	4	120.3	91	4.43	2.140	16.70	0	1	5	2
27	Lotus Europa	30.4	4	95.1	113	3.77	1.513	16.90	1	1	5	2
28	Ford Pantera L	15.8	8	351.0	264	4.22	3.170	14.50	0	1	5	4
29	Ferrari Dino	19.7	6	145.0	175	3.62	2.770	15.50	0	1	5	6
31	Volvo 142E	21.4	4	121.0	109	4.11	2.780	18.60	1	1	4	2

	car_model	mpg	cyl	disp	hp	drat	wt	vs	am	gear	carb
0	Mazda RX4	21.0	6	160	110.0	3.90	2.62	0	1	4	4
1	Mazda RX4 Wag	21.0	6	NaN	110.0	NaN	2.875	0	1	4	4
2	Datsun 710	NaN	4	108	NaN	3.85	NaN	1	1	4	1
3	Hornet 4 Drive	999.0	6	NaN	NaN	3.08	3.215	1	0	3	1
4	Datsun 710	22.8	4	NaN	93.0	3.85	2.32	1	1	4	1
5	Valiant	18.1	6	225	105.0	2.76	3.46	1	0	3	1
6	Duster 360	14.3	8	360	245.0	3.21	3.57	0	0	3	4
7	Valiant 2	18.1	6	225	105.0	2.76	NaN	1	0	3	1
8	Valiant	18.1	6	225	105.0	2.76	3.46	1	0	3	1
9	Merc 280	19.2	6	167.6	123.0	3.92	3.44	1	0	4	4
10	Merc 280C	17.8	6	167.6	123.0	3.92	3.44	1	0	4	4
11	Merc 450SE	16.4	8	275.8	180.0	3.07	4.07	0	0	3	3
12	Merc 450SL	17.3	8	275.8	180.0	3.07	NaN	0	0	3	3
13	Merc 450SLC	15.2	8	275.8	180.0	3.07	3.78	0	0	3	3
14	Cadillac Fleetwood	10.4	8	NaN	205.0	2.93	5.25	0	0	3	4
15	Lincoln Continental	10.4	8	460	215.0	3.00	5.424	0	0	3	4
16	Chrysler Imperial	14.7	8	440	230.0	3.23	5.345	0	0	3	4
17	Fiat 128	32.4	4	NaN	66.0	4.08	2.2	1	1	4	1
18	Honda Civic	30.4	4	75.7	52.0	4.93	1.615	1	1	4	2
19	Toyota Corolla	33.9	4	71.1	65.0	4.22	1.835	1	1	4	1
20	Toyota Corona	21.5	4	120.1	97.0	3.70	2.465	1	0	3	1
21	Dodge Challenger	15.5	8	NaN	150.0	2.76	NaN	0	0	3	2
22	AMC Javelin	15.2	8	304	150.0	3.15	3.435	0	0	3	2
23	Camaro Z28	13.3	8	350	245.0	3.73	3.84	0	0	3	4
24	Pontiac Firebird	19.2	8	400	175.0	3.08	3.845	0	0	3	2
25	Fiat X1-9	27.3	4	NaN	66.0	4.08	NaN	1	1	4	1
26	Porsche 914-2	26.0	4	120.3	91.0	4.43	2.14	0	1	5	2
27	Lotus Europa	30.4	4	95.1	113.0	3.77	NaN	1	1	5	2
28	Ford Pantera L	15.8	8	NaN	264.0	4.22	3.17	0	1	5	4
29	Ferrari Dino	19.7	6	145	175.0	3.62	2.77	0	1	5	6
30	Maserati Bora	15.0	8	NaN	335.0	3.54	3.57	0	1	5	8
31	Volvo 142E	21.4	4	121	109.0	4.11	2.78	1	1	4	2

orderyear	2015	2016	2017	2018
category
Furniture	NaN	8.477093	16.645257	8.288444
Office Supplies	NaN	-9.581824	34.034351	33.792106
Technology	NaN	-7.130049	39.060729	20.041435

orderyear	2015	2016	2017	2018
category
Furniture	NaN	-44.753489	130.828682	-56.632017
Office Supplies	NaN	11.092248	39.688767	13.334936
Technology	NaN	55.883907	18.714631	27.430650

	mean radius	mean texture	mean perimeter	mean area	mean smoothness	mean compactness	mean concavity	mean concave points	mean symmetry	mean fractal dimension	radius error	texture error	perimeter error	area error	smoothness error	compactness error	concavity error	concave points error	symmetry error	fractal dimension error	worst radius	worst texture	worst perimeter	worst area	worst smoothness	worst compactness	worst concavity	worst concave points	worst symmetry	worst fractal dimension	outcome
mean radius	1.000000	0.323782	0.997855	0.987357	0.170581	0.506124	0.676764	0.822529	0.147741	-0.311631	0.679090	-0.097317	0.674172	0.735864	-0.222600	0.206000	0.194204	0.376169	-0.104321	-0.042641	0.969539	0.297008	0.965137	0.941082	0.119616	0.413463	0.526911	0.744214	0.163953	0.007066	0.730029
mean texture	0.323782	1.000000	0.329533	0.321086	-0.023389	0.236702	0.302418	0.293464	0.071401	-0.076437	0.275869	0.386358	0.281673	0.259845	0.006614	0.191975	0.143293	0.163851	0.009127	0.054458	0.352573	0.912045	0.358040	0.343546	0.077503	0.277830	0.301025	0.295316	0.105008	0.119205	0.415185
mean perimeter	0.997855	0.329533	1.000000	0.986507	0.207278	0.556936	0.716136	0.850977	0.183027	-0.261477	0.691765	-0.086761	0.693135	0.744983	-0.202694	0.250744	0.228082	0.407217	-0.081629	-0.005523	0.969476	0.303038	0.970387	0.941550	0.150549	0.455774	0.563879	0.771241	0.189115	0.051019	0.742636
mean area	0.987357	0.321086	0.986507	1.000000	0.177028	0.498502	0.685983	0.823269	0.151293	-0.283110	0.732562	-0.066280	0.726628	0.800086	-0.166777	0.212583	0.207660	0.372320	-0.072497	-0.019887	0.962746	0.287489	0.959120	0.959213	0.123523	0.390410	0.512606	0.722017	0.143570	0.003738	0.708984
mean smoothness	0.170581	-0.023389	0.207278	0.177028	1.000000	0.659123	0.521984	0.553695	0.557775	0.584792	0.301467	0.068406	0.296092	0.246552	0.332375	0.318943	0.248396	0.380676	0.200774	0.283607	0.213120	0.036072	0.238853	0.206718	0.805324	0.472468	0.434926	0.503053	0.394309	0.499316	0.358560
mean compactness	0.506124	0.236702	0.556936	0.498502	0.659123	1.000000	0.883121	0.831135	0.602641	0.565369	0.497473	0.046205	0.548905	0.455653	0.135299	0.738722	0.570517	0.642262	0.229977	0.507318	0.535315	0.248133	0.590210	0.509604	0.565541	0.865809	0.816275	0.815573	0.510223	0.687382	0.596534
mean concavity	0.676764	0.302418	0.716136	0.685983	0.521984	0.883121	1.000000	0.921391	0.500667	0.336783	0.631925	0.076218	0.660391	0.617427	0.098564	0.670279	0.691270	0.683260	0.178009	0.449301	0.688236	0.299879	0.729565	0.675987	0.448822	0.754968	0.884103	0.861323	0.409464	0.514930	0.696360
mean concave points	0.822529	0.293464	0.850977	0.823269	0.553695	0.831135	0.921391	1.000000	0.462497	0.166917	0.698050	0.021480	0.710650	0.690299	0.027653	0.490424	0.439167	0.615634	0.095351	0.257584	0.830318	0.292752	0.855923	0.809630	0.452753	0.667454	0.752399	0.910155	0.375744	0.368661	0.776614
mean symmetry	0.147741	0.071401	0.183027	0.151293	0.557775	0.602641	0.500667	0.462497	1.000000	0.479921	0.303379	0.128053	0.313893	0.223970	0.187321	0.421659	0.342627	0.393298	0.449137	0.331786	0.185728	0.090651	0.219169	0.177193	0.426675	0.473200	0.433721	0.430297	0.699826	0.438413	0.330499
mean fractal dimension	-0.311631	-0.076437	-0.261477	-0.283110	0.584792	0.565369	0.336783	0.166917	0.479921	1.000000	0.000111	0.164174	0.039830	-0.090170	0.401964	0.559837	0.446630	0.341198	0.345007	0.688132	-0.253691	-0.051269	-0.205151	-0.231854	0.504942	0.458798	0.346234	0.175325	0.334019	0.767297	-0.012838
radius error	0.679090	0.275869	0.691765	0.732562	0.301467	0.497473	0.631925	0.698050	0.303379	0.000111	1.000000	0.213247	0.972794	0.951830	0.164514	0.356065	0.332358	0.513346	0.240567	0.227754	0.715065	0.194799	0.719684	0.751548	0.141919	0.287103	0.380585	0.531062	0.094543	0.049559	0.567134
texture error	-0.097317	0.386358	-0.086761	-0.066280	0.068406	0.046205	0.076218	0.021480	0.128053	0.164174	0.213247	1.000000	0.223171	0.111567	0.397243	0.231700	0.194998	0.230283	0.411621	0.279723	-0.111690	0.409003	-0.102242	-0.083195	-0.073658	-0.092439	-0.068956	-0.119638	-0.128215	-0.045655	-0.008303
perimeter error	0.674172	0.281673	0.693135	0.726628	0.296092	0.548905	0.660391	0.710650	0.313893	0.039830	0.972794	0.223171	1.000000	0.937655	0.151075	0.416322	0.362482	0.556264	0.266487	0.244143	0.697201	0.200371	0.721031	0.730713	0.130054	0.341919	0.418899	0.554897	0.109930	0.085433	0.556141
area error	0.735864	0.259845	0.744983	0.800086	0.246552	0.455653	0.617427	0.690299	0.223970	-0.090170	0.951830	0.111567	0.937655	1.000000	0.075150	0.284840	0.270895	0.415730	0.134109	0.127071	0.757373	0.196497	0.761213	0.811408	0.125389	0.283257	0.385100	0.538166	0.074126	0.017539	0.548236
smoothness error	-0.222600	0.006614	-0.202694	-0.166777	0.332375	0.135299	0.098564	0.027653	0.187321	0.401964	0.164514	0.397243	0.151075	0.075150	1.000000	0.336696	0.268685	0.328429	0.413506	0.427374	-0.230691	-0.074743	-0.217304	-0.182195	0.314457	-0.055558	-0.058298	-0.102007	-0.107342	0.101480	-0.067016
compactness error	0.206000	0.191975	0.250744	0.212583	0.318943	0.738722	0.670279	0.490424	0.421659	0.559837	0.356065	0.231700	0.416322	0.284840	0.336696	1.000000	0.801268	0.744083	0.394713	0.803269	0.204607	0.143003	0.260516	0.199371	0.227394	0.678780	0.639147	0.483208	0.277878	0.590973	0.292999
concavity error	0.194204	0.143293	0.228082	0.207660	0.248396	0.570517	0.691270	0.439167	0.342627	0.446630	0.332358	0.194998	0.362482	0.270895	0.268685	0.801268	1.000000	0.771804	0.309429	0.727372	0.186904	0.100241	0.226680	0.188353	0.168481	0.484858	0.662564	0.440472	0.197788	0.439329	0.253730
concave points error	0.376169	0.163851	0.407217	0.372320	0.380676	0.642262	0.683260	0.615634	0.393298	0.341198	0.513346	0.230283	0.556264	0.415730	0.328429	0.744083	0.771804	1.000000	0.312780	0.611044	0.358127	0.086741	0.394999	0.342271	0.215351	0.452888	0.549592	0.602450	0.143116	0.310655	0.408042
symmetry error	-0.104321	0.009127	-0.081629	-0.072497	0.200774	0.229977	0.178009	0.095351	0.449137	0.345007	0.240567	0.411621	0.266487	0.134109	0.413506	0.394713	0.309429	0.312780	1.000000	0.369078	-0.128121	-0.077473	-0.103753	-0.110343	-0.012662	0.060255	0.037119	-0.030413	0.389402	0.078079	-0.006522
fractal dimension error	-0.042641	0.054458	-0.005523	-0.019887	0.283607	0.507318	0.449301	0.257584	0.331786	0.688132	0.227754	0.279723	0.244143	0.127071	0.427374	0.803269	0.727372	0.611044	0.369078	1.000000	-0.037488	-0.003195	-0.001000	-0.022736	0.170568	0.390159	0.379975	0.215204	0.111094	0.591328	0.077972
worst radius	0.969539	0.352573	0.969476	0.962746	0.213120	0.535315	0.688236	0.830318	0.185728	-0.253691	0.715065	-0.111690	0.697201	0.757373	-0.230691	0.204607	0.186904	0.358127	-0.128121	-0.037488	1.000000	0.359921	0.993708	0.984015	0.216574	0.475820	0.573975	0.787424	0.243529	0.093492	0.776454
worst texture	0.297008	0.912045	0.303038	0.287489	0.036072	0.248133	0.299879	0.292752	0.090651	-0.051269	0.194799	0.409003	0.200371	0.196497	-0.074743	0.143003	0.100241	0.086741	-0.077473	-0.003195	0.359921	1.000000	0.365098	0.345842	0.225429	0.360832	0.368366	0.359755	0.233027	0.219122	0.456903
worst perimeter	0.965137	0.358040	0.970387	0.959120	0.238853	0.590210	0.729565	0.855923	0.219169	-0.205151	0.719684	-0.102242	0.721031	0.761213	-0.217304	0.260516	0.226680	0.394999	-0.103753	-0.001000	0.993708	0.365098	1.000000	0.977578	0.236775	0.529408	0.618344	0.816322	0.269493	0.138957	0.782914
worst area	0.941082	0.343546	0.941550	0.959213	0.206718	0.509604	0.675987	0.809630	0.177193	-0.231854	0.751548	-0.083195	0.730713	0.811408	-0.182195	0.199371	0.188353	0.342271	-0.110343	-0.022736	0.984015	0.345842	0.977578	1.000000	0.209145	0.438296	0.543331	0.747419	0.209146	0.079647	0.733825
worst smoothness	0.119616	0.077503	0.150549	0.123523	0.805324	0.565541	0.448822	0.452753	0.426675	0.504942	0.141919	-0.073658	0.130054	0.125389	0.314457	0.227394	0.168481	0.215351	-0.012662	0.170568	0.216574	0.225429	0.236775	0.209145	1.000000	0.568187	0.518523	0.547691	0.493838	0.617624	0.421465
worst compactness	0.413463	0.277830	0.455774	0.390410	0.472468	0.865809	0.754968	0.667454	0.473200	0.458798	0.287103	-0.092439	0.341919	0.283257	-0.055558	0.678780	0.484858	0.452888	0.060255	0.390159	0.475820	0.360832	0.529408	0.438296	0.568187	1.000000	0.892261	0.801080	0.614441	0.810455	0.590998
worst concavity	0.526911	0.301025	0.563879	0.512606	0.434926	0.816275	0.884103	0.752399	0.433721	0.346234	0.380585	-0.068956	0.418899	0.385100	-0.058298	0.639147	0.662564	0.549592	0.037119	0.379975	0.573975	0.368366	0.618344	0.543331	0.518523	0.892261	1.000000	0.855434	0.532520	0.686511	0.659610
worst concave points	0.744214	0.295316	0.771241	0.722017	0.503053	0.815573	0.861323	0.910155	0.430297	0.175325	0.531062	-0.119638	0.554897	0.538166	-0.102007	0.483208	0.440472	0.602450	-0.030413	0.215204	0.787424	0.359755	0.816322	0.747419	0.547691	0.801080	0.855434	1.000000	0.502528	0.511114	0.793566
worst symmetry	0.163953	0.105008	0.189115	0.143570	0.394309	0.510223	0.409464	0.375744	0.699826	0.334019	0.094543	-0.128215	0.109930	0.074126	-0.107342	0.277878	0.197788	0.143116	0.389402	0.111094	0.243529	0.233027	0.269493	0.209146	0.493838	0.614441	0.532520	0.502528	1.000000	0.537848	0.416294
worst fractal dimension	0.007066	0.119205	0.051019	0.003738	0.499316	0.687382	0.514930	0.368661	0.438413	0.767297	0.049559	-0.045655	0.085433	0.017539	0.101480	0.590973	0.439329	0.310655	0.078079	0.591328	0.093492	0.219122	0.138957	0.079647	0.617624	0.810455	0.686511	0.511114	0.537848	1.000000	0.323872
outcome	0.730029	0.415185	0.742636	0.708984	0.358560	0.596534	0.696360	0.776614	0.330499	-0.012838	0.567134	-0.008303	0.556141	0.548236	-0.067016	0.292999	0.253730	0.408042	-0.006522	0.077972	0.776454	0.456903	0.782914	0.733825	0.421465	0.590998	0.659610	0.793566	0.416294	0.323872	1.000000

	Sales
Month
2016-01-01	266
2016-02-01	146
2016-03-01	183
2016-04-01	119
2016-05-01	180

	age	workclass	fnlwgt	education	educationNum	marital	occupation	relationship	race	sex	capGain	HoursWeek	NativeCountry	category
0	39	State-gov	77516	Bachelors	13	Never-married	Adm-clerical	Not-in-family	White	Male	2174	40	United-States	<=50K
1	50	Self-emp-not-inc	83311	Bachelors	13	Married-civ-spouse	Exec-managerial	Husband	White	Male	0	13	United-States	<=50K
2	38	Private	215646	HS-grad	9	Divorced	Handlers-cleaners	Not-in-family	White	Male	0	40	United-States	<=50K
3	53	Private	234721	11th	7	Married-civ-spouse	Handlers-cleaners	Husband	Black	Male	0	40	United-States	<=50K
4	28	Private	338409	Bachelors	13	Married-civ-spouse	Prof-specialty	Wife	Black	Female	0	40	Cuba	<=50K

	IP	Time	URL	Staus
0	10.128.2.1	15/Feb/2018:03:10:38	GET /home.php HTTP/1.1	302
1	10.128.2.1	15/Feb/2018:03:10:38	GET /login.php HTTP/1.1	200
2	10.128.2.1	15/Feb/2018:03:10:39	GET /css/bootstrap.min.css HTTP/1.1	200
3	10.131.0.1	15/Feb/2018:03:10:39	GET /css/font-awesome.min.css HTTP/1.1	200
4	10.130.2.1	15/Feb/2018:03:10:39	GET /css/normalize.css HTTP/1.1	200

PART - 1 (1 to 10)¶

1. Extracting data with Regular Expression¶

2. Pandas Pivot Table¶

Adding color Styling¶

3. Pandas cut method, continuous to categorical data¶

Classify Wine Quality (bad wine, good wine and premium wine)¶

4. Split strings to columns, expand¶

Add 2 more Columns Author_Firstname and Author_Lastname¶

Creer une nouvelle colonne de Reviews en %¶

5. Remove Outliers by Filtering¶

Suppression des valeurs aberrantes par filtrage¶

z value for entire data5¶

6. Handle missing values with dropna()¶

Checking the missing values¶

Supprimer tous NaN > 60% en utilisant thresh¶

7. Pandas Apply Function¶

Etant donner que nous avons de valeur manquantes, nous devons utiliser la méthode suivante:¶

8. Pandas set_option for formating, change default max_columns¶

Nous voulons voir toutes les colonne sans les (...)¶

9. Extracting Month & Year as separate columns from Pandas Date column¶

10. Percentage change function in Pandas DataFrame.¶

Python Pandas Tutorial: Top 40 Useful Tricks Part-2¶

11. Correlation Matrix Plot Pandas DataFrame¶

12. Import number column as string¶

13. Read date column from data as Index in DataFrame.¶

14. Read data only specific columns¶

15. Find percentage of records with missing values¶

16. Reading Multiple Files¶

17. Rearrange Numerical and Categorical Columns¶

18. Label encoding multiple columns¶

19. Finding correllation b/w features and target variable¶

20. Replace special chars in column names with '_' VIP¶

To remove all the special caracters¶

My top 25 pandas tricks¶

Add 2 more Columns `Author_Firstname` and `Author_Lastname`¶

Supprimer tous NaN > 60% en utilisant `thresh`¶