add level column

This commit is contained in:
Benjamin Bertrand 2017-03-07 17:24:15 +03:00
parent 0abd2be854
commit 0fba0017fe
1 changed files with 92 additions and 18 deletions

View File

@ -3,7 +3,7 @@
import pandas as pd
import numpy as np
from math import ceil
from math import ceil, floor
import logging
logger = logging.getLogger(__name__)
@ -47,7 +47,7 @@ def note_to_rep(x):
return x["Note"]
def note_to_mark(x):
""" Compute the mark when it is a "Nivea" note
""" Compute the mark when it is a "Niveau" note
:param x: dictionnary with "Niveau", "Note" and "Bareme" keys
@ -72,6 +72,46 @@ def note_to_mark(x):
return x["Note"] * x["Bareme"] / 3
return x["Note"]
def note_to_level(x):
""" Compute the level ("na",0,1,2,3).
"na" correspond to "no answer"
:param x: dictionnary with "Niveau", "Note" and "Bareme" keys
>>> 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"],
... "Question":["Q1"]+["Q2"]+["Q1"]+["Q2"]+["Q1"]+["Q1"] + ["Q1"]+["Q2"]+["Q1"]+["Q2"]+["Q1"]+["Q1"],
... "Date":["16/09/2016"]*4+["01/10/2016"]*2 + ["16/09/2016"]*4+["01/10/2016"]*2,
... "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, np.nan, 1.5, 1, 3, 0.666, 1, 1.5, 1, 2, 3],
... }
>>> df = pd.DataFrame(d)
>>> note_to_level(df.loc[0])
3
>>> note_to_level(df.loc[1])
1
>>> note_to_level(df.loc[2])
'na'
>>> note_to_level(df.loc[3])
3
>>> note_to_level(df.loc[5])
3
>>> note_to_level(df.loc[10])
2
"""
if pd.isnull(x["Note"]):
return "na"
if x["Niveau"]:
return int(x["Note"])
else:
return int(ceil(x["Note"] / x["Bareme"] * 3))
def question_uniq_formater(row):
""" Create a kind of unique description of the question
@ -154,6 +194,39 @@ def compute_marks(df):
"""
return df[["Note", "Niveau", "Bareme"]].apply(note_to_mark, axis=1)
def compute_level(df):
""" Add Mark column to df
:param df: DataFrame with "Note", "Niveau" and "Bareme" columns.
>>> 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"],
... "Question":["Q1"]+["Q2"]+["Q1"]+["Q2"]+["Q1"]+["Q1"] + ["Q1"]+["Q2"]+["Q1"]+["Q2"]+["Q1"]+["Q1"],
... "Date":["16/09/2016"]*4+["01/10/2016"]*2 + ["16/09/2016"]*4+["01/10/2016"]*2,
... "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":[np.nan, 0.33, 2, 1.5, 1, 3, 0.666, 1, 1.5, 1, 2, 3],
... }
>>> df = pd.DataFrame(d)
>>> compute_level(df)
0 na
1 1
2 3
3 3
4 1
5 3
6 2
7 3
8 3
9 2
10 2
11 3
dtype: object
"""
return df[["Note", "Niveau", "Bareme"]].apply(note_to_level, axis=1)
def compute_latex_rep(df):
""" Add Latex_rep column to df
@ -340,24 +413,24 @@ 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, nan, 0, 0, nan, nan, nan],
... "Note":[1, 0.33, 2, 1.5, 1, 3, np.nan, 0, 0, np.nan, np.nan, np.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 1.00 1 1.00 Ex1 Q1
1 E1 N1 0.33 0.33 0.33 Ex1 Q2
2 E1 N1 2.00 2 1.00 Ex2 Q1
3 E1 N1 1.50 1.5 0.75 Ex2 Q2
4 E1 N2 0.67 \RepU 0.33 Ex1 Q1
5 E1 N2 2.00 \RepT 1.00 Ex2 Q1
6 E2 N1 NaN ?? NaN Ex1 Q1
7 E2 N1 0.00 0 0.00 Ex1 Q2
8 E2 N1 0.00 0 0.00 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
>>> quest_df[['Eleve', "Nom", "Mark", "Latex_rep", "Normalized", "Uniq_quest", "Level"]]
Eleve Nom Mark Latex_rep Normalized Uniq_quest Level
0 E1 N1 1.00 1 1.00 Ex1 Q1 3
1 E1 N1 0.33 0.33 0.33 Ex1 Q2 1
2 E1 N1 2.00 2 1.00 Ex2 Q1 3
3 E1 N1 1.50 1.5 0.75 Ex2 Q2 3
4 E1 N2 0.67 \RepU 0.33 Ex1 Q1 1
5 E1 N2 2.00 \RepT 1.00 Ex2 Q1 3
6 E2 N1 NaN ?? NaN Ex1 Q1 na
7 E2 N1 0.00 0 0.00 Ex1 Q2 0
8 E2 N1 0.00 0 0.00 Ex2 Q1 0
9 E2 N1 NaN ?? NaN Ex2 Q2 na
10 E2 N2 NaN \NoRep NaN Ex1 Q1 na
11 E2 N2 NaN \NoRep NaN Ex2 Q1 na
>>> exo_df[['Eleve', "Nom", "Exercice", "Mark", "Normalized"]]
Eleve Nom Exercice Mark Normalized
0 E1 N1 Ex1 1.5 0.75
@ -376,8 +449,9 @@ def digest_flat_df(flat_df):
3 1 E2 N2 1 4.0 01/10/2016 NaN NaN
"""
# Remove data with "nn" (non notés)
df = flat_df.copy()[flat_df["Note"] != "nn"]
df = flat_df.copy()[flat_df["Note"].astype("object") != "nn"]
df["Mark"] = compute_marks(df)
df["Level"] = compute_level(df)
df["Latex_rep"] = compute_latex_rep(df)
df["Normalized"] = compute_normalized(df)
df["Uniq_quest"] = compute_question_description(df)