Pandas DataFrame – marifnst

i hope this post will be helpful for all beginner of python, especially to pandas user. i use winpython as the environment.

sample_data.csv

COL1	COL2
DATA_1	1
DATA_2	2
DATA_3	3
DATA_4	4
DATA_5	5
DATA_6	6
DATA_7	7
DATA_8	8
DATA_9	9
DATA_10	10

sample_data_odd.csv

COL2	IS_ODD
1	2
2	1
3	2
4	1
5	2
6	1
7	2
8	1
9	2
10	1

source code

import pandas as pd
 
# =================================================================
#load csv
sample_data_odd = pd.read_csv(r"D:\nitip\tulisan\2018\Python\Panda_Data_Frame\sample_data_odd.csv")
sample_data = pd.read_csv(r"D:\nitip\tulisan\2018\Python\Panda_Data_Frame\sample_data.csv")
 
# =================================================================
print("============================ basic dataframe")
print(sample_data.head(3))
 
sample_data['COL3'] = sample_data['COL2'].apply( lambda x : x if x % 2 == 0 else 0)
print("============================ after applying lambda (check odd number)")
print(sample_data.head(3))
 
sample_data = sample_data.rename(columns={'COL1':'DATA_ID', 'COL3':'IS_ODD'})
print("============================ rename column")
print(sample_data.head(3))
 
sample_data = sample_data.loc[:, ['DATA_ID', 'COL2']]
print("============================ replace / slice IS_ODD column")
print(sample_data.head(3))
 
sample_data = pd.merge(left = sample_data, right = sample_data_odd, how='left', on=['COL2'])
print("============================ sample merge")
print(sample_data.head(3))
 
sample_data = sample_data.drop(['COL2'], axis = 1)
print("============================ drop column")
print(sample_data.head(3))
 
sample_data_concat_nodrop = pd.concat( [sample_data, sample_data], axis = 0)
print("============================ concat column with no drop index")
print(sample_data_concat_nodrop)
 
sample_data_concat_drop = pd.concat( [sample_data, sample_data], axis = 0).reset_index(drop = True)
print("============================ concat column with drop / reset index")
print(sample_data_concat_drop)
 
sample_data["COL_NEW"] = sample_data['DATA_ID'].apply( lambda x : int(x[5:len(x)]))
print("============================ sample group by & sum,mean,median")
print(sample_data.groupby(['IS_ODD'])['COL_NEW'].sum())
print(sample_data.groupby(['IS_ODD'])['COL_NEW'].mean())
print(sample_data.groupby(['IS_ODD'])['COL_NEW'].median())
 
sample_data = sample_data.loc[ sample_data['IS_ODD'].isin([1]), :].reset_index(drop = True)
print("============================ sample isin syntax (filtering IS_ODD equal to 1)")
print(sample_data)
 
print("============================ sample join sample_data_ori with sample_data")
#print(sample_data.join(sample_data_ori))
sample_data_ori = pd.read_csv(r"D:\nitip\tulisan\2018\Python\Panda_Data_Frame\sample_data.csv")
print(sample_data_ori.join(sample_data))
 
print("============================ sample max")
print(sample_data.max())
 
print("============================ sample min")
print(sample_data.min())

import pandas as pd # ================================================================= #load csv sample_data_odd = pd.read_csv(r"D:\nitip\tulisan\2018\Python\Panda_Data_Frame\sample_data_odd.csv") sample_data = pd.read_csv(r"D:\nitip\tulisan\2018\Python\Panda_Data_Frame\sample_data.csv") # ================================================================= print("============================ basic dataframe") print(sample_data.head(3)) sample_data['COL3'] = sample_data['COL2'].apply( lambda x : x if x % 2 == 0 else 0) print("============================ after applying lambda (check odd number)") print(sample_data.head(3)) sample_data = sample_data.rename(columns={'COL1':'DATA_ID', 'COL3':'IS_ODD'}) print("============================ rename column") print(sample_data.head(3)) sample_data = sample_data.loc[:, ['DATA_ID', 'COL2']] print("============================ replace / slice IS_ODD column") print(sample_data.head(3)) sample_data = pd.merge(left = sample_data, right = sample_data_odd, how='left', on=['COL2']) print("============================ sample merge") print(sample_data.head(3)) sample_data = sample_data.drop(['COL2'], axis = 1) print("============================ drop column") print(sample_data.head(3)) sample_data_concat_nodrop = pd.concat( [sample_data, sample_data], axis = 0) print("============================ concat column with no drop index") print(sample_data_concat_nodrop) sample_data_concat_drop = pd.concat( [sample_data, sample_data], axis = 0).reset_index(drop = True) print("============================ concat column with drop / reset index") print(sample_data_concat_drop) sample_data["COL_NEW"] = sample_data['DATA_ID'].apply( lambda x : int(x[5:len(x)])) print("============================ sample group by & sum,mean,median") print(sample_data.groupby(['IS_ODD'])['COL_NEW'].sum()) print(sample_data.groupby(['IS_ODD'])['COL_NEW'].mean()) print(sample_data.groupby(['IS_ODD'])['COL_NEW'].median()) sample_data = sample_data.loc[ sample_data['IS_ODD'].isin([1]), :].reset_index(drop = True) print("============================ sample isin syntax (filtering IS_ODD equal to 1)") print(sample_data) print("============================ sample join sample_data_ori with sample_data") #print(sample_data.join(sample_data_ori)) sample_data_ori = pd.read_csv(r"D:\nitip\tulisan\2018\Python\Panda_Data_Frame\sample_data.csv") print(sample_data_ori.join(sample_data)) print("============================ sample max") print(sample_data.max()) print("============================ sample min") print(sample_data.min())

CMIIW

Leave a Reply Cancel reply