Fix typos in README and code comments

.pre-commit-config.yaml

@@ -86,3 +86,13 @@ repos:
             "--convention=google",
             "--match=^((?!test).)*$",
           ]
+
+  - repo: https://github.com/codespell-project/codespell
+    rev: v2.3.0
+    hooks:
+      - id: codespell
+        name: codespell
+        description: Checks for common misspellings in text files.
+        entry: codespell -L fallow
+        language: python
+        types: [text]

README.md

@@ -108,7 +108,7 @@ python -m "instageo.data.chip_creator" \
 
 #### Launch Training
 
-Before launching training, modify the path to chips and segementation maps in each split
+Before launching training, modify the path to chips and segmentation maps in each split
 ```python
 for split in ["train", "val", "test"]:
     root_dir = "locust_breeding"

instageo/data/README.md

@@ -19,7 +19,7 @@ By providing gelocated observation records containing longitude, latitude, date
 - For each record, create a corresponding temporal series of HLS granules
 - Create a set of all HLS granules
 - Download the required bands from each granule
-- Create and save chips and segementation maps
+- Create and save chips and segmentation maps
 
 Chip creator is particularly useful for geospatial image segmentation where large satellite images are segmented into smaller chips for training geospatial models (such as [Prithvi](https://huggingface.co/ibm-nasa-geospatial/Prithvi-100M)) using image segmentation objective.
 

instageo/data/hls_utils.py

@@ -173,7 +173,7 @@ def get_hls_tile_info(
 
     Retrieves a summary of all tiles required for a given dataset. The summary contains
     the desired start and end date for each HLS tile. Also retrieves a list of queries
-    that can be used to retieve the tiles for each observation in `data`.
+    that can be used to retrieve the tiles for each observation in `data`.
 
     Args:
         data (pd.DataFrame): A dataframe containing observation records.

instageo/model/README.md

@@ -9,7 +9,7 @@ The InstaGeo Model component is designed for training, validation and inference
 See `requirements.txt`
 
 ## Features
-- Supports both classsification and regression tasks
+- Supports both classification and regression tasks
 - Accepts both temporal and non-temporal inputs
 - Custom models with [Prithvi_100M](https://huggingface.co/ibm-nasa-geospatial/Prithvi-100M) backbone
 - Training, Validation and Inference runs

notebooks/InstaGeo_Demo.ipynb

@@ -808,7 +808,7 @@
       "outputs": [],
       "source": [
         "import urllib\n",
-        "print(\"Password/Enpoint IP for localtunnel is:\",urllib.request.urlopen('https://ipv4.icanhazip.com').read().decode('utf8').strip(\"\\n\"))"
+        "print(\"Password/Endpoint IP for localtunnel is:\",urllib.request.urlopen('https://ipv4.icanhazip.com').read().decode('utf8').strip(\"\\n\"))"
       ]
     },
     {