> For the complete documentation index, see [llms.txt](https://lwang010.gitbook.io/longw/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://lwang010.gitbook.io/longw/mlops/chap-3.-hardware-maintain/storage-data-center/case-monitor-storage-increase.md).

# \[Case] Monitor storage increase

def getFileSummaryByMonth(directory, path):

 folder = path

 filepaths = \[os.path.join(folder, f) for f in os.listdir(folder)]

stats = {}

 i = 0

for file in filepaths:

  \# Get the unique date for each file

  file\_name = file

  last\_Mod = os.stat(file).st\_ctime

  size = os.stat(file).st\_size

  str1 = time.ctime(os.path.getmtime(file\_name)) 

  datetime\_object = datetime.datetime.strptime(str1, '%a %b %d %H:%M:%S %Y')

  date = datetime\_object.strftime("%Y-%m") # 06/07/2013

  \# Add values to dictionary

  stats = {'Index': i, 'file\_name': file\_name, 'date': date, 'size': size}

  print(stats)

  i = i+1

  dict\_obj.add(i, stats)

\# Create duplicate file info dictionary

 filestats = stats

\# Convert to dataframe

 filestats = pd.DataFrame.from\_dict(dict\_obj,orient='index')

 print(filestats)

\# Aggregate files by unique month and filesize

 filestats\["date"] = pd.to\_datetime(filestats\["date"])

 grouped\_by\_month\_stats = filestats.groupby(filestats\['date'].dt.strftime('%Y-%m'))\['size'].sum().sort\_values()

 print(grouped\_by\_month\_stats)

 df = pd.Series.to\_frame(grouped\_by\_month\_stats)

 df.sort\_values(by='date', inplace=True, ascending=False)

\# Write each filtered dataframe to a different worksheet in the same Excel file

 df.to\_excel(writer, sheet\_name=directory)

Usage:

getFileSummaryByMonth('reporting\_service', 'C://first\_path//')

getFileSummaryByMonth('archive\_service', 'C://second\_path//')

getFileSummaryByMonth('search\_service', 'C://third\_path//')

Ref: <https://towardsdatascience.com/projecting-and-visualizing-infrastructure-growth-trends-with-python-1e578d9e4260>