Removing nan from entire data frame

djarecka · djarecka · commit 92e34b9007e9 · 2025-01-31T18:21:53.000-05:00
diff --git a/reproschema/redcap2reproschema.py b/reproschema/redcap2reproschema.py
@@ -569,9 +569,7 @@ def process_csv(csv_file, abs_folder_path, schema_context_url, protocol_name):
     )
 
     # Clean string values in the dataframe
-    object_columns = df.select_dtypes(include=["object"]).columns
-    for col in object_columns:
-        df[col] = df[col].astype(str).replace("nan", "")
+    df = df.astype(str).replace("nan", "")
 
     # Initialize structures for each unique form
     unique_forms = df["Form Name"].unique()

Original file line number	Diff line number	Diff line change
`@@ -569,9 +569,7 @@ def process_csv(csv_file, abs_folder_path, schema_context_url, protocol_name):`
`569`	`569`	`)`
`570`	`570`
`571`	`571`	`# Clean string values in the dataframe`
`572`		`- object_columns = df.select_dtypes(include=["object"]).columns`
`573`		`- for col in object_columns:`
`574`		`- df[col] = df[col].astype(str).replace("nan", "")`
	`572`	`+ df = df.astype(str).replace("nan", "")`
`575`	`573`
`576`	`574`	`# Initialize structures for each unique form`
`577`	`575`	`unique_forms = df["Form Name"].unique()`