diff --git a/README.md b/README.md index 7f76756..e2765ed 100644 --- a/README.md +++ b/README.md @@ -81,7 +81,7 @@ from afes import afe TARGET_FOLDER = "" # Run exploration on the files -df_files = afe.explore(TARGET_FOLDER) +df_files = afe.explore_files(TARGET_FOLDER) df_files ``` @@ -108,7 +108,7 @@ with python as the following code, or using a Jupyter Using the dataframe `df_files` generated in the explore phase, you can generate working python pandas code to be used. -the function `generate()` will generate python code to load the files using +The function `generate_files()` will generate python code to load the files using `pandas`. ```python @@ -118,8 +118,8 @@ from afes import afe TARGET_FOLDER = "" OUTPUT_FOLDER = "" -df_files = afe.explore(TARGET_FOLDER) -afe.generate(df_files) +df_files = afe.explore_files(TARGET_FOLDER) +afe.generate_code(df_files) ``` The generated code will look like this: @@ -159,10 +159,10 @@ TARGET_FOLDER = "" OUTPUT_FOLDER = "" # Run exploration on the files -df_files = afe.explore(TARGET_FOLDER) +df_files = afe.explore_files(TARGET_FOLDER) -afe.profile(df_files, profile_tool="ydata-profiling", output_path=OUTPUT_FOLDER) # or -afe.profile(df_files, profile_tool="sweetviz", output_path=OUTPUT_FOLDER) +afe.profile_files(df_files, profile_tool="ydata-profiling", output_path=OUTPUT_FOLDER) # or +afe.profile_files(df_files, profile_tool="sweetviz", output_path=OUTPUT_FOLDER) ``` By default, it will process the files using `ydata-profiling` by size order diff --git a/src/afes/databases.ini.template b/src/afes/databases.ini.template deleted file mode 100644 index 43f04ae..0000000 --- a/src/afes/databases.ini.template +++ /dev/null @@ -1,8 +0,0 @@ -[] -db_engine = postgres -host = -schema = -catalog = -user = -password = -port = diff --git a/src/afes/notebook-example.ipynb b/src/afes/notebook-example.ipynb index fcd3599..4f160a9 100644 --- a/src/afes/notebook-example.ipynb +++ b/src/afes/notebook-example.ipynb @@ -26,7 +26,7 @@ "outputs": [], "source": [ "# Run exploration on the files\n", - "df_files = afe.explore(TARGET_FOLDER)\n", + "df_files = afe.explore_files(TARGET_FOLDER)\n", "df_files" ] }, @@ -37,7 +37,7 @@ "outputs": [], "source": [ "# Generate pandas code to load the files\n", - "afe.generate(df_files)" + "afe.generate_code(df_files)" ] }, { @@ -47,8 +47,8 @@ "outputs": [], "source": [ "# Run profiling on each file\n", - "afe.profile(df_files, profile_tool=\"ydata-profiling\", output_path=OUTPUT_FOLDER)\n", - "afe.profile(df_files, profile_tool=\"sweetviz\", output_path=OUTPUT_FOLDER)" + "afe.profile_files(df_files, profile_tool=\"ydata-profiling\", output_path=OUTPUT_FOLDER)\n", + "afe.profile_files(df_files, profile_tool=\"sweetviz\", output_path=OUTPUT_FOLDER)" ] } ],