(hopefully) a more intuitive solution

aleks-krasowski · aleks-krasowski · commit ec08aa7b2c5f · 2021-11-25T18:03:12.000+01:00
diff --git a/06-2021-11-26/src/_solutions/features_above_threshold.py b/06-2021-11-26/src/_solutions/features_above_threshold.py
@@ -1,5 +1,6 @@
 ## solution challenge 
 def features_above_threshold(df, threshold=0.5):    
-    cols2keep = df.notnull().sum()/df.shape[0] > threshold 
-    rv = df.columns[cols2keep.values]
-    return rv
+    n_samples = df.shape[0]
+    cols2keep = df.notnull().sum()/n_samples > threshold 
+    cols2keep = cols2keep.loc[cols2keep == True].index
+    return cols2keep
diff --git a/06-2021-11-26/src/_solutions/infere_mission_data.py b/06-2021-11-26/src/_solutions/infere_mission_data.py
@@ -1,2 +1,2 @@
 ## solution challenge 
-df_clean["Mission Date"] = pd.to_datetime(df_clean["Mission Date"], infer_datetime_format=True)
+df_clean["Mission Date"] = pd.to_datetime(df_clean["Mission Date"])

Original file line number	Diff line number	Diff line change
`@@ -1,2 +1,2 @@`
`1`	`1`	`## solution challenge`
`2`		`-df_clean["Mission Date"] = pd.to_datetime(df_clean["Mission Date"], infer_datetime_format=True)`
	`2`	`+df_clean["Mission Date"] = pd.to_datetime(df_clean["Mission Date"])`