Ufdjrw

could anyone advise me how to apply this code to several csv in one folder? Then, save the modified csv to another folder and each separately? In short, I need to automate it.

I need to automatically load the csv file, execute the code, save the newly modified csv file, and then repeat it to the next csv file in the folder.

import pandas as pd
import datetime as dt
import numpy as np
from numpy import nan as Nan

path = "C://Users//Zemi4//Desktop//csv//A-001.csv"

df = pd.read_csv(path,delimiter=";")

df['ta'] = pd.to_numeric(df['ta'])
df['tw'] = pd.to_numeric(df['tw'])

df["time_str"] = [dt.datetime.strptime(d, "%d.%m.%Y %H:%M:%S") for d in df["time"]]
df["time_str"] = [d.date() for d in df["time_str"]]
df["time_str"] = pd.to_datetime(df["time_str"])
df["time_zaokrouhleny"]=df["time_str"]

def analyza(pozadovane_data):

 new_list = []

 new_df = pd.DataFrame(new_list)

 new_df=df.loc[df["time_str"] == pozadovane_data,["ta","tw", "zone", "time_zaokrouhleny"]]

 counter = new_df.ta.count()

 if counter < 24:
 for i in range(counter,24):
 new_df.loc[i] = [Nan for n in range(4)]
 new_df["ta"]= new_df.ta.fillna(0)
 new_df["tw"] = new_df.tw.fillna(0)
 new_df["zone"] = new_df.zone.fillna(0)
 new_df["time_zaokrouhleny"]=new_df.time_zaokrouhleny.fillna(new_df.time_zaokrouhleny.min())

 elif counter > 24:
 counter_list = list(range(24,counter))
 new_df = new_df.drop(new_df.index[counter_list])

 new_df["time_oprava"] = [dt.datetime.combine(d.date(),dt.time(1,0)) for d in new_df["time_zaokrouhleny"]]

 s = 0
 cas_list = []

 for d in new_df["time_oprava"]:
 d =d + dt.timedelta(hours=s)
 #print(d)
 #print(s)
 cas_list.append(d)
 s = s + 1

 se = pd.Series(cas_list)

 new_df['time_oprava'] = se.values

 new_df['Validace'] = (new_df['ta'] != 0) & (new_df['tw'] != 0)

 new_df['Rozdil'] = new_df['ta'] - new_df['tw']

 new_df.rename(columns="ta": "Skutecna teplota", "tw": "Pozadovana teplota", "time_oprava": "Cas", "zone": "Mistnost", inplace = True)

 new_df.index = new_df['Cas']

 return new_df

start = dt.datetime(2010,10,6)
end = dt.datetime(2010,12,27)

date_range = []
date_range = [start + dt.timedelta(days=x) for x in range(0,(end-start).days)]

new_list = []

vysledek_df =pd.DataFrame(new_list)

for d in date_range:
 pom = analyza(d)
 vysledek_df = vysledek_df.append(pom,ignore_index=True)
 vysledek_df.pop('time_zaokrouhleny')
 vysledek_df.to_csv('C://Users//Zemi4//Desktop//zpr//A-001.csv', encoding='utf-8', index=False)

The code itself works correctly. Thank you for your advice.

Simplest way is to use glob. Just give the folder_path and output_path as per your requirements and use the sample code below. I commented the code to help you understand the code.

import os
import glob

folder_path = 'path/to/folder/' # path to folder containing .csv files
output_path = 'path/to/output/folder/' # path to output folder

for file in glob.glob(folder_path + '*.csv'): # only loads .csv files from the folder
 df = pd.read_csv(file, delimiter=";") # read .csv file

 # Do something

 df.to_csv(output_path + 'modified_' + str(os.path.basename(file)), encoding='utf-8', index=False) # saves modified .csv file to output_path

You want to use os.listdir() to find the contents of the directory, then parameterize the file path in a new function. You can then loop over a list of directories retrieved via os.walk() and run the function for each one.

import os

def run(file_directory):

 filelist = os.listdir(file_directory)

 for path in filelist:

 df = pd.read_csv(path,delimiter=";")

 # etc.

 df.to_csv(os.path.join(file_directory, 'output.csv'))

If you need to create a new directory, you can use os.mkdir(newpath)

Can you still advise on how to parameterize the function?