mkdir data_copy
cp -r data data_copy
rm -r data
ps
df
vmstat
jobs
ps aux|grep {process_name}
https://github.com/dfirst-education/sample/blob/dev/_sample_execute_py_from_sh/sample.md
with open('.\\input.jsonl') as f:
for line in f:
if line.find('{"target_words": "') >= 0:
with open('.\\output.jsonl', "a") as f:
f.write(line)
https://github.com/dfirst-education/sample/blob/dev/dataframe_create.ipynb
import pandas as pd
# changing format
pd.get_option("display.max_columns")
pd.get_option("display.max_colwidth")
pd.set_option('display.max_columns', 50)
pd.set_option('display.max_colwidth', 100)
# reading excel file to dataframe
df = pd.read_excel('.\\input_target.xlsx', index_col=0)
# reading csv file to dataframe
df = pd.read_csv('.\\ input_target.csv', header=0)
# reading jsonl file to dataframe
df = pd.read_json('.\\ input_target.jsonl', orient='records', lines=True)
# showing dataframe
df [0:2]
print(df.shape)
df.dtypes
# Replacing NaN with Zero 0
df = df.fillna(0)
# Changing column type
df['column1'] = df[' column1'].astype('object')
# selecting rows with a condition
df_selected_rows = df.query('col1 in ["value1", " value2"]')
# selecting columns
df_selected_columns = df.loc[:, ["column1", " column2"]]
df_selected_columns = df.iloc[:, [0, 1]]
# writing dataframe to csv file
df.to_csv("output_target.csv")
# writing dataframe to json file
df [["column1", " column2", " column3"]].to_json("output_target.json", orient='records')
# resetting index
df_selected_rows.reset_index(inplace=True, drop=True)
# sample of creating dataframe and inserting data with index
googleapikey = 'API Key' gmaps = googlemaps.Client(key=googleapikey) df_location = pd.DataFrame(columns=["city", "lat", "lng"]) i = 0 with open("./city-list.csv", "r", encoding="utf-8_sig") as f: reader = csv.reader(f, delimiter='\t') for row in reader: result = gmaps.geocode(row[0]) if len(result) != 0: lat = result[0]["geometry"]["location"]["lat"] lng = result[0]["geometry"]["location"]["lng"] data = {'city' : row[0], 'lat' : lat, 'lng' : lng} df_location.loc[i] = data # specifying index i += 1 time.sleep(1.0)
# outer join
df3 = pd.merge(df, df2, on="column1", how="outer")
Key Bindings for Visual Studio Code
https://code.visualstudio.com/docs/getstarted/keybindings
The code can be wrapped by the width of the editor.
Can normalize Json files
Can edit or replace selected words.
Can execute git command and so on.
Can do comment-out for multi-rows