pandas读写数据方法

1. pandas操作csv

1.1 读写csv

import sys
import pandas as pd
input_file = sys.argv[1]
output_file = sys.argv[2]
data_frame = pd.read_csv(input_file)
print(data_frame)
data_frame.to_csv(output_file, index=False)

1.2 过滤规定条件下的数据

import pandas as pd
import sys
input_file = sys.argv[1]
output_file = sys.argv[2]
data_frame = pd.read_csv(input_file)
data_frame['Cost'] = data_frame['Cost'].str.strip('$').astype(float)
data_frame_value_meets_condition = data_frame.loc[(data_frame['Supplier Name']\
.str.contains('Z')) | (data_frame['Cost'] > 600.0), :]
data_frame_value_meets_condition.to_csv(output_file, index=False)

1.3 过滤满足某些条件的数据

import pandas as pd
import sys
input_file = sys.argv[1]
output_file = sys.argv[2]
data_frame = pd.read_csv(input_file)
important_dates = ['1/20/14', '1/30/14']
data_frame_value_in_set = data_frame.loc[data_frame['Purchase Date'].\
isin(important_dates), :]
data_frame_value_in_set.to_csv(output_file, index=False)

1.4 过滤字段中的数据

import pandas as pd
import sys
input_file = sys.argv[1]
output_file = sys.argv[2]
data_frame = pd.read_csv(input_file)
data_frame_value_matches_pattern = data_frame.loc[data_frame['Invoice Number'].\
str.startswith("001-"), :]
data_frame_value_matches_pattern.to_csv(output_file, index=False)

1.5 选择某些列的内容

import pandas as pd
import sys
input_file = sys.argv[1]
output_file = sys.argv[2]
data_frame = pd.read_csv(input_file)
data_frame_column_by_index = data_frame.iloc[:, [0, 3]]
data_frame_column_by_index.to_csv(output_file, index=False)

1.6 根据列名选择列数据

import pandas as pd
import sys
input_file = sys.argv[1]
output_file = sys.argv[2]
data_frame = pd.read_csv(input_file)
data_frame_column_by_name = data_frame.loc[:, ['Invoice Number', 'Purchase Date']]
data_frame_column_by_name.to_csv(output_file, index=False)

1.7 剔除无用行的数据

import pandas as pd
import sys
input_file = sys.argv[1]
output_file = sys.argv[2]
data_frame = pd.read_csv(input_file, header=None)
data_frame = data_frame.drop([