Skip to content

Instantly share code, notes, and snippets.

@rchardptrsn
Last active August 20, 2023 01:29
Show Gist options
  • Save rchardptrsn/1e54a6b254c5a589f071c991f49e2c0b to your computer and use it in GitHub Desktop.
Save rchardptrsn/1e54a6b254c5a589f071c991f49e2c0b to your computer and use it in GitHub Desktop.
combine files.py
import glob as glob
import pandas as pd
#define path to CSV files
path = r'ndvi data/*.csv'
#identify all CSV files
all_files = glob.glob(path)
#merge all CSV files into one DataFrame
fireNDVI = pd.concat((pd.read_csv(f) for f in all_files), ignore_index=True)
##############################
# Get a list of missing values
missing_values = list(set(gdf['OBJECTID'].unique().tolist()) - set(fireNDVI['OBJECTID'].unique().tolist()))
# Subset gdf to isolate the missing values
missing_rows = gdf[gdf['OBJECTID'].isin(missing_values)]
print(f"There are {gdf['OBJECTID'].nunique() - fireNDVI['OBJECTID'].nunique()} missing OBJECTIDs")
print(f"These missing values are {missing_values}")
##############################
# Download the NDVI for the missing records
# Collect all
collectAllNDVI(missing_rows)
print('Complete.')
##############################
# Re-combine the data files include any missing files
# identify all CSV files in the path
all_files = glob.glob(path)
#merge all CSV files into one DataFrame
fireNDVI = pd.concat((pd.read_csv(f) for f in all_files), ignore_index=True)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment