Feat: format_score

recopytex/datalib/on_score_column.py

@@ -43,6 +43,57 @@ def is_none_score(x, score_config):
     return x["score"] in none_values or pd.isnull(x["score"])
 
 
+def format_score(x, score_config):
+    """Make sure that score have the appropriate format
+
+    >>> import pandas as pd
+    >>> d = {"Eleve":["E1"]*6,
+    ...    "score_rate": [1]*6,
+    ...    "is_leveled":[0]+[1]*5,
+    ...    "score":[0.33,  ".", "a", 1, 2, 3],
+    ...    }
+    >>> score_config = {
+    ...   'BAD': {'value': 0, 'numeric_value': 0},
+    ...   'FEW': {'value': 1, 'numeric_value': 1},
+    ...   'NEARLY': {'value': 2, 'numeric_value': 2},
+    ...   'GOOD': {'value': 3, 'numeric_value': 3},
+    ...   'NOTFILLED': {'value': '', 'numeric_value': 'None'},
+    ...   'NOANSWER': {'value': '.', 'numeric_value': 0},
+    ...   'ABS': {'value': 'a', 'numeric_value': 'None'}
+    ...    }
+    >>> df = pd.DataFrame(d)
+    >>> df.apply(lambda x:format_score(x, score_config), axis=1)
+    0    0.33
+    1       .
+    2       a
+    3       1
+    4       2
+    5       3
+    dtype: object
+    >>> format_score({"score": "1.0", "is_leveled": 1}, score_config)
+    1
+    >>> format_score({"score": "3.0", "is_leveled": 1}, score_config)
+    3
+    >>> format_score({"score": 4, "is_leveled": 1}, score_config)
+    Traceback (most recent call last):
+        ...
+    ValueError: 4 (<class 'int'>) can't be a score
+
+    """
+    if not x["is_leveled"]:
+        return float(x["score"])
+
+    try:
+        score = int(float(x["score"]))
+    except ValueError:
+        score = str(x["score"])
+
+    if score in [v["value"] for v in score_config.values()]:
+        return score
+
+    raise ValueError(f"{x['score']} ({type(x['score'])}) can't be a score")
+
+
 def score_to_numeric_score(x, score_config):
     """Convert a score to the corresponding numeric value
 
@@ -81,7 +132,7 @@ def score_to_numeric_score(x, score_config):
 
 
 def score_to_mark(x, score_max, rounding=lambda x: round(x, 2)):
-    """Compute the mark from the score
+    """Compute the mark from "score" which have to be filtered and in numeric form
 
     if the item is leveled then the score is multiply by the score_rate
     otherwise it copies the score
@@ -92,39 +143,38 @@ def score_to_mark(x, score_max, rounding=lambda x: round(x, 2)):
     :return: the mark
 
     >>> import pandas as pd
-    >>> d = {"Eleve":["E1"]*6 + ["E2"]*6,
-    ...    "score_rate":[1]*2+[2]*2+[2]*2 + [1]*2+[2]*2+[2]*2,
-    ...    "is_leveled":[0]*4+[1]*2 + [0]*4+[1]*2,
-    ...    "score":[1, 0.33, 2, 1.5, 1, 3,   0.666, 1, 1.5, 1.2, 2, 3],
+    >>> d = {"Eleve":["E1"]*7,
+    ...    "score_rate": [1]*7,
+    ...    "is_leveled":[0]+[1]*6,
+    ...    "score":[0.33, "", ".", "a", 1, 2, 3],
+    ...    }
+    >>> score_config = {
+    ...   'BAD': {'value': 0, 'numeric_value': 0},
+    ...   'FEW': {'value': 1, 'numeric_value': 1},
+    ...   'NEARLY': {'value': 2, 'numeric_value': 2},
+    ...   'GOOD': {'value': 3, 'numeric_value': 3},
+    ...   'NOTFILLED': {'value': '', 'numeric_value': 'None'},
+    ...   'NOANSWER': {'value': '.', 'numeric_value': 0},
+    ...   'ABS': {'value': 'a', 'numeric_value': 'None'}
     ...    }
     >>> df = pd.DataFrame(d)
-    >>> df.loc[0]
-    Eleve          E1
-    score_rate      1
-    is_leveled      0
-    score         1.0
-    Name: 0, dtype: object
-    >>> score_to_mark(df.loc[0], 3)
-    1.0
-    >>> df.loc[10]
-    Eleve          E2
-    score_rate      2
-    is_leveled      1
-    score         2.0
-    Name: 10, dtype: object
-    >>> score_to_mark(df.loc[10], 3)
-    1.33
+    >>> df = df[~df.apply(lambda x:is_none_score(x, score_config), axis=1)]
+    >>> df["score"] = df.apply(lambda x:score_to_numeric_score(x, score_config), axis=1)
+    >>> df.apply(lambda x:score_to_mark(x, 3), axis=1)
+    0    0.33
+    2    0.00
+    4    0.33
+    5    0.67
+    6    1.00
+    dtype: float64
     >>> from .on_value import round_half_point
-    >>> score_to_mark(df.loc[10], 3, round_half_point)
-    1.5
-    >>> df.loc[1]
-    Eleve           E1
-    score_rate       1
-    is_leveled       0
-    score         0.33
-    Name: 1, dtype: object
-    >>> score_to_mark(df.loc[1], 3)
-    0.33
+    >>> df.apply(lambda x:score_to_mark(x, 3, round_half_point), axis=1)
+    0    0.5
+    2    0.0
+    4    0.5
+    5    0.5
+    6    1.0
+    dtype: float64
     """
     if x["is_leveled"]:
         if x["score"] not in list(range(score_max + 1)):