lafrite/repytex
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

NaN management

Browse Source
This commit is contained in:
Benjamin Bertrand 2016-11-22 15:20:23 +03:00
parent ee6274fd0a
commit b2b9723fd9
2 changed files with 34 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

37
notes_tools/tools/df_marks_manip.py
View File

@ -150,7 +150,7 @@ def compute_marks(df):
11 2.000000
dtype: float64
"""
return df[["Note", "Niveau", "Bareme"]].apply(note_to_mark, axis=1).fillna(0)
return df[["Note", "Niveau", "Bareme"]].apply(note_to_mark, axis=1)
def compute_latex_rep(df):
""" Add Latex_rep column to df
@ -317,8 +317,9 @@ def compute_eval_marks(df):
return eval_m
def digest_flat_df(flat_df):
""" Compute necessary element to make a flat df usable for analysis.
r""" Compute necessary element to make a flat df usable for analysis.
>>> from numpy import nan
>>> d = {"Eleve":["E1"]*6 + ["E2"]*6,
... "Nom": ["N1"]*4+["N2"]*2 + ["N1"]*4+["N2"]*2,
... "Exercice":["Ex1"]*2+["Ex2"]*2+["Ex1"]+["Ex2"] + ["Ex1"]*2+["Ex2"]*2+["Ex1"]+["Ex2"],
@ -327,10 +328,40 @@ def digest_flat_df(flat_df):
... "Trimestre": ["1"]*12,
... "Bareme":[1]*2+[2]*2+[2]*2 + [1]*2+[2]*2+[2]*2,
... "Niveau":[0]*4+[1]*2 + [0]*4+[1]*2,
... "Note":[1, 0.33, 2, 1.5, 1, 3, 0.666, 1, 1.5, 1, 2, 3],
... "Note":[1, 0.33, 2, 1.5, 1, 3, nan, 0, 0, nan, nan, nan],
... }
>>> df = pd.DataFrame(d)
>>> quest_df, exo_df, eval_df = digest_flat_df(df)
>>> quest_df[['Eleve', "Nom", "Mark", "Latex_rep", "Normalized", "Uniq_quest"]]
Eleve Nom Mark Latex_rep Normalized Uniq_quest
0 E1 N1 1.000000 1 1.000000 Ex1 Q1
1 E1 N1 0.330000 0.33 0.330000 Ex1 Q2
2 E1 N1 2.000000 2 1.000000 Ex2 Q1
3 E1 N1 1.500000 1.5 0.750000 Ex2 Q2
4 E1 N2 0.666667 \RepU 0.333333 Ex1 Q1
5 E1 N2 2.000000 \RepT 1.000000 Ex2 Q1
6 E2 N1 NaN ?? NaN Ex1 Q1
7 E2 N1 0.000000 0 0.000000 Ex1 Q2
8 E2 N1 0.000000 0 0.000000 Ex2 Q1
9 E2 N1 NaN ?? NaN Ex2 Q2
10 E2 N2 NaN \NoRep NaN Ex1 Q1
11 E2 N2 NaN \NoRep NaN Ex2 Q1
>>> exo_df[['Eleve', "Nom", "Exercice", "Mark", "Normalized"]]
Eleve Nom Exercice Mark Normalized
0 E1 N1 Ex1 1.5 0.750
1 E1 N1 Ex2 3.5 0.875
2 E1 N2 Ex1 1.0 0.500
3 E1 N2 Ex2 2.0 1.000
4 E2 N1 Ex1 0.0 0.000
5 E2 N1 Ex2 0.0 0.000
6 E2 N2 Ex1 NaN NaN
7 E2 N2 Ex2 NaN NaN
>>> eval_df[['Eleve', "Nom", "Mark", "Normalized"]]
Eleve Nom Mark Normalized
0 E1 N1 5.0 0.833333
1 E1 N2 3.0 0.750000
2 E2 N1 0.0 0.000000
3 E2 N2 NaN NaN
"""
df = flat_df.copy()
df["Mark"] = compute_marks(flat_df)

BIN
samples/312.xlsx
View File

Binary file not shown.