Feat: import html for 404 layout

see https://dash.plotly.com/urls

.gitignore

@@ -122,3 +122,7 @@ dmypy.json
 
 # Pyre type checker
 .pyre/
+
+# vim
+.vim
+

README.md

@@ -6,3 +6,29 @@ Cette fois ci, on utilise:
 - Des fichiers yaml pour les infos sur les élèves
 - Des notebooks pour l'analyse
 - Papermill pour produire les notesbooks à partir de template
+
+## Les fichiers CSV
+
+les paramètres sont décris dans ./recopytex/config.py
+
+### Descriptions des questions
+
+- Trimestre
+- Nom
+- Date
+- Exercice
+- Question
+- Competence
+- Domaine
+- Commentaire
+- Bareme
+- Est_nivele
+
+
+### Valeurs pour notes les élèves
+
+- Score: 0, 1, 2, 3
+- Pas de réponses: .
+- Absent: a
+- Dispensé: (vide)
+

example/Tribe1/210112_DS.csv

@@ -0,0 +1,5 @@
+Trimestre,Nom,Date,Exercice,Question,Competence,Domaine,Commentaire,Bareme,Est_nivele,Star Tice,Umberto Dingate,Starlin Crangle,Humbert Bourcq,Gabriella Handyside,Stewart Eaves,Erick Going,Ase Praton,Rollins Planks,Dunstan Sarjant,Stacy Guiton,Ange Stanes,Amabelle Elleton,Darn Broomhall,Dyan Chatto,Keane Rennebach,Nari Paulton,Brandy Wase,Jaclyn Firidolfi,Violette Lockney
+1,DS,12/01/2021,Exercice 1,1,Calculer,Plop,Coucou,1,1,,,1,0,1,2,3,0,3,3,2,,1,,,,,,,
+1,DS,12/01/2021,Exercice 1,2,Calculer,C'est trop chouette!,Coucou,1,1,,,1,2,,,3,3,,,,,2,,,,,,,
+1,DS,12/01/2021,Exercice 1,3,Calculer,Null,Coucou,1,1,,,,3,2,,,,,,,,3,,,,,,,
+1,DS,12/01/2021,Exercice 1,3,Calculer,Nié,DChic,1,1,,,,2,.,,,,,,,,,,,,,,,

example/Tribe1/210122_DS6.csv

@@ -0,0 +1,5 @@
+Trimestre,Nom,Date,Exercice,Question,Competence,Domaine,Commentaire,Bareme,Est_nivele,Star Tice,Umberto Dingate,Starlin Crangle,Humbert Bourcq,Gabriella Handyside,Stewart Eaves,Erick Going,Ase Praton,Rollins Planks,Dunstan Sarjant,Stacy Guiton,Ange Stanes,Amabelle Elleton,Darn Broomhall,Dyan Chatto,Keane Rennebach,Nari Paulton,Brandy Wase,Jaclyn Firidolfi,Violette Lockney
+1,DS6,22/01/2021,Exercice 1,Sait pas,,,,,,,,,,,,,,,,,,,,,,,,,
+1,DS6,22/01/2021,Exercice 1,Ha,,,,,,,,,,,,,,,,,,,,,,,,,
+1,DS6,22/01/2021,Exercice 1,,,,,,,,,,,,,,,,,,,,,,,,,,
+1,DS6,22/01/2021,Exercice 2,grr,,,,,,,,,,,,,,,,,,,,,,,,,

example/recoconfig.yml

@@ -0,0 +1,13 @@
+---
+source: ./
+output: ./
+templates: templates/
+
+tribes:
+    Tribe1:
+        name: Tribe1
+        type: Type1
+        students: tribe1.csv
+    Tribe2:
+        name: Tribe2
+        students: tribe2.csv

example/tribe1.csv

@@ -0,0 +1,21 @@
+Nom,email
+Star Tice,stice0@jalbum.net
+Umberto Dingate,udingate1@tumblr.com
+Starlin Crangle,scrangle2@wufoo.com
+Humbert Bourcq,hbourcq3@g.co
+Gabriella Handyside,ghandyside4@patch.com
+Stewart Eaves,seaves5@ycombinator.com
+Erick Going,egoing6@va.gov
+Ase Praton,apraton7@va.gov
+Rollins Planks,rplanks8@delicious.com
+Dunstan Sarjant,dsarjant9@naver.com
+Stacy Guiton,sguitona@themeforest.net
+Ange Stanes,astanesb@marriott.com
+Amabelle Elleton,aelletonc@squidoo.com
+Darn Broomhall,dbroomhalld@cisco.com
+Dyan Chatto,dchattoe@npr.org
+Keane Rennebach,krennebachf@dot.gov
+Nari Paulton,npaultong@gov.uk
+Brandy Wase,bwaseh@ftc.gov
+Jaclyn Firidolfi,jfiridolfii@reuters.com
+Violette Lockney,vlockneyj@chron.com

example/tribe2.csv

@@ -0,0 +1,21 @@
+Nom,email
+Elle McKintosh,emckintosh0@1und1.de
+Ty Megany,tmegany1@reuters.com
+Pippa Borrows,pborrows2@a8.net
+Sonny Eskrick,seskrick3@123-reg.co.uk
+Mollee Britch,mbritch4@usda.gov
+Ingram Plaistowe,iplaistowe5@purevolume.com
+Fay Vanyard,fvanyard6@sbwire.com
+Nancy Rase,nrase7@omniture.com
+Rachael Ruxton,rruxton8@bravesites.com
+Tallie Rushmer,trushmer9@home.pl
+Seward MacIlhagga,smacilhaggaa@hatena.ne.jp
+Lizette Searl,lsearlb@list-manage.com
+Talya Mannagh,tmannaghc@webnode.com
+Jordan Witherbed,jwitherbedd@unesco.org
+Reagan Botcherby,rbotcherbye@scientificamerican.com
+Libbie Shoulder,lshoulderf@desdev.cn
+Abner Khomich,akhomichg@youtube.com
+Zollie Kitman,zkitmanh@forbes.com
+Fiorenze Durden,fdurdeni@feedburner.com
+Kevyn Race,kracej@seattletimes.com

recoconfig.yml

@@ -1,4 +0,0 @@
----
-source: sheets/
-output: reports/
-templates: templates/

recopytex/__init__.py

@@ -1,5 +0,0 @@
-#!/usr/bin/env python
-# encoding: utf-8
-
-from .csv_extraction import flat_df_students, flat_df_for
-from .df_marks_manip import pp_q_scores

recopytex/config.py

@@ -1,30 +0,0 @@
-#!/usr/bin/env python
-# encoding: utf-8
-
-NO_ST_COLUMNS = {
-    "term": "Trimestre",
-    "assessment": "Nom",
-    "date": "Date",
-    "exercise": "Exercice",
-    "question": "Question",
-    "competence": "Competence",
-    "theme": "Domaine",
-    "comment": "Commentaire",
-    "score_rate": "Bareme",
-    "is_leveled": "Est_nivele",
-}
-
-COLUMNS = {
-    **NO_ST_COLUMNS,
-    "student": "Eleve",
-    "score": "Score",
-    "mark": "Note",
-    "level": "Niveau",
-    "normalized": "Normalise",
-}
-
-VALIDSCORE = {
-    "NOTFILLED": "",  # The item is not scored yet
-    "NOANSWER": ".",  # Student gives no answer (this score will impact the fianl mark)
-    "ABS": "a",  # Student has absent (this score won't be impact the final mark)
-}

recopytex/csv_extraction.py

@@ -1,119 +0,0 @@
-#!/usr/bin/env python
-# encoding: utf-8
-
-""" Extracting data from xlsx files """
-
-import pandas as pd
-from .config import NO_ST_COLUMNS, COLUMNS, VALIDSCORE
-
-pd.set_option("Precision", 2)
-
-
-def try_replace(x, old, new):
-    try:
-        return str(x).replace(old, new)
-    except ValueError:
-        return x
-
-
-def extract_students(df, no_student_columns=NO_ST_COLUMNS.values()):
-    """ Extract the list of students from df 
-
-    :param df: the dataframe
-    :param no_student_columns: columns that are not students
-    :return: list of students
-    """
-    students = df.columns.difference(no_student_columns)
-    return students
-
-
-def flat_df_students(
-    df, no_student_columns=NO_ST_COLUMNS.values(), postprocessing=True
-):
-    """ Flat the dataframe by returning a dataframe with on student on each line
-
-    :param df: the dataframe (one row per questions)
-    :param no_student_columns: columns that are not students
-    :return: dataframe with one row per questions and students
-
-    Columns of csv files:
-
-    - NO_ST_COLUMNS meta data on questions
-    - one for each students
-
-    This function flat student's columns to "student" and "score"
-    """
-    students = extract_students(df, no_student_columns)
-    scores = []
-    for st in students:
-        scores.append(
-            pd.melt(
-                df,
-                id_vars=no_student_columns,
-                value_vars=st,
-                var_name=COLUMNS["student"],
-                value_name=COLUMNS["score"],
-            ).dropna(subset=[COLUMNS["score"]])
-        )
-    if postprocessing:
-        return postprocess(pd.concat(scores))
-    return pd.concat(scores)
-
-
-def flat_df_for(
-    df, student, no_student_columns=NO_ST_COLUMNS.values(), postprocessing=True
-):
-    """ Extract the data only for one student
-
-    :param df: the dataframe (one row per questions)
-    :param no_student_columns: columns that are not students
-    :return: dataframe with one row per questions and students
-
-    Columns of csv files:
-
-    - NO_ST_COLUMNS meta data on questions
-    - one for each students
-
-    """
-    students = extract_students(df, no_student_columns)
-    if student not in students:
-        raise KeyError("This student is not in the table")
-    st_df = df[list(no_student_columns) + [student]]
-    st_df = st_df.rename(columns={student: COLUMNS["score"]}).dropna(
-        subset=[COLUMNS["score"]]
-    )
-    if postprocessing:
-        return postprocess(st_df)
-    return st_df
-
-
-def postprocess(df):
-    """ Postprocessing score dataframe 
-
-    - Replace na with an empty string
-    - Replace "NOANSWER" with -1
-    - Turn commas number to dot numbers
-    """
-
-    df[COLUMNS["question"]].fillna("", inplace=True)
-    df[COLUMNS["exercise"]].fillna("", inplace=True)
-    df[COLUMNS["comment"]].fillna("", inplace=True)
-    df[COLUMNS["competence"]].fillna("", inplace=True)
-
-    df[COLUMNS["score"]] = pd.to_numeric(
-        df[COLUMNS["score"]]
-        .replace(VALIDSCORE["NOANSWER"], -1)
-        .apply(lambda x: try_replace(x, ",", "."))
-    )
-    df[COLUMNS["score_rate"]] = pd.to_numeric(
-        df[COLUMNS["score_rate"]].apply(lambda x: try_replace(x, ",", ".")),
-        errors="coerce",
-    )
-
-    return df
-
-
-# -----------------------------
-# Reglages pour 'vim'
-# vim:set autoindent expandtab tabstop=4 shiftwidth=4:
-# cursor: 16 del

recopytex/dashboard/app.py

@@ -0,0 +1,20 @@
+#!/usr/bin/env python
+# encoding: utf-8
+
+import dash
+import flask
+
+from .layout.layout import layout
+
+server = flask.Flask(__name__)
+app = dash.Dash(
+    __name__,
+    server=server,
+    suppress_callback_exceptions=True,
+    meta_tags=[{"name": "viewport", "content": "width=device-width, initial-scale=1"}],
+)
+
+
+app.layout = layout
+server = app.server
+

recopytex/dashboard/common/formating.py

@@ -0,0 +1,23 @@
+#!/usr/bin/env python
+# encoding: utf-8
+
+
+def highlight_scores(highlight_columns, score_color):
+    """ Cells style in a datatable for scores
+
+    :param highlight_columns: columns to highlight
+    :param value_color: dictionnary {"score": "color"}
+
+    """
+    hight = []
+    for v, color in score_color.items():
+        if v:
+            hight += [
+                {
+                    "if": {"filter_query": "{{{}}} = {}".format(col, v), "column_id": col},
+                    "backgroundColor": color,
+                    "color": "white",
+                }
+                for col in highlight_columns
+            ]
+    return hight

recopytex/dashboard/index.py

@@ -0,0 +1,8 @@
+#!/usr/bin/env python
+# encoding: utf-8
+
+from .app import app, server
+from .routes import render_page_content
+
+if __name__ == "__main__":
+    app.run_server(debug=True)

recopytex/dashboard/layout/layout.py

@@ -0,0 +1,9 @@
+#!/usr/bin/env python
+# encoding: utf-8
+
+import dash_html_components as html
+import dash_core_components as dcc
+
+content = html.Div(id="page-content")
+
+layout = html.Div([dcc.Location(id="url"), content])

recopytex/dashboard/pages/exams_scores/app.py

@@ -0,0 +1,112 @@
+#!/usr/bin/env python
+# encoding: utf-8
+
+import dash_html_components as html
+import dash_core_components as dcc
+from .models import get_tribes, get_exams
+from .callbacks import *
+
+layout = html.Div(
+    children=[
+        html.Header(
+            children=[
+                html.H1("Analyse des notes"),
+                html.P("Dernière sauvegarde", id="lastsave"),
+            ],
+        ),
+        html.Main(
+            children=[
+                html.Section(
+                    children=[
+                        html.Div(
+                            children=[
+                                "Classe: ",
+                                dcc.Dropdown(
+                                    id="tribe",
+                                    options=[
+                                        {"label": t["name"], "value": t["name"]}
+                                        for t in get_tribes().values()
+                                    ],
+                                    value=next(iter(get_tribes().values()))["name"],
+                                ),
+                            ],
+                        ),
+                        html.Div(
+                            children=[
+                                "Evaluation: ",
+                                dcc.Dropdown(id="exam_select"),
+                            ],
+                        ),
+                    ],
+                    id="selects",
+                ),
+                html.Section(
+                    children=[
+                        html.Div(
+                            children=[
+                                dash_table.DataTable(
+                                    id="final_score_table",
+                                    columns=[
+                                        {"name": "Étudiant", "id": "student_name"},
+                                        {"name": "Note", "id": "mark"},
+                                        {"name": "Barème", "id": "score_rate"},
+                                    ],
+                                )
+                            ],
+                            id="final_score_table_container",
+                        ),
+                        html.Div(
+                            children=[
+                                dash_table.DataTable(
+                                    id="score_statistics_table",
+                                    columns=[],
+                                )
+                            ],
+                            id="score_statistics_table_container",
+                        ),
+                        html.Div(
+                            children=[
+                                dcc.Graph(
+                                    id="fig_exam_histo",
+                                    config={"displayModeBar": False},
+                                )
+                            ],
+                            id="fig_exam_histo_container",
+                        ),
+                        html.Div(
+                            children=[
+                                dcc.Graph(
+                                    id="fig_questions_bar",
+                                    config={"displayModeBar": False},
+                                )
+                            ],
+                            id="fig_questions_bar_container",
+                        ),
+                    ],
+                    id="analysis",
+                ),
+                html.Section(
+                    children=[
+                        dash_table.DataTable(
+                            id="scores_table",
+                            columns=[],
+                            style_data_conditional=[],
+                            fixed_columns={},
+                            editable=True,
+                            style_table={"minWidth": "100%"},
+                            style_cell={
+                                "minWidth": "100px",
+                                "width": "100px",
+                                "maxWidth": "100px",
+                                "overflow": "hidden",
+                                "textOverflow": "ellipsis",
+                            },
+                        )
+                    ],
+                    id="edit",
+                ),
+            ],
+        ),
+        dcc.Store(id="scores"),
+    ],
+)

recopytex/dashboard/pages/exams_scores/callbacks.py

@@ -0,0 +1,216 @@
+#!/usr/bin/env python
+# encoding: utf-8
+
+from dash.dependencies import Input, Output, State
+from dash.exceptions import PreventUpdate
+import plotly.graph_objects as go
+import dash_table
+import json
+import pandas as pd
+import numpy as np
+
+from recopytex.dashboard.app import app
+from recopytex.dashboard.common.formating import highlight_scores
+
+from .models import (
+    get_tribes,
+    get_exams,
+    get_unstack_scores,
+    get_students_from_exam,
+    get_score_colors,
+    get_level_color_bar,
+    score_to_final_mark,
+    stack_scores,
+    pivot_score_on,
+)
+
+
+@app.callback(
+    [
+        Output("exam_select", "options"),
+        Output("exam_select", "value"),
+    ],
+    [Input("tribe", "value")],
+)
+def update_exams_choices(tribe):
+    if not tribe:
+        raise PreventUpdate
+    exams = get_exams(tribe)
+    exams.reset_index(inplace=True)
+    if not exams.empty:
+        return [
+            {"label": e["name"], "value": e.to_json()} for i, e in exams.iterrows()
+        ], exams.loc[0].to_json()
+    return [], None
+
+
+@app.callback(
+    [
+        Output("scores_table", "columns"),
+        Output("scores_table", "data"),
+        Output("scores_table", "style_data_conditional"),
+        Output("scores_table", "fixed_columns"),
+    ],
+    [
+        Input("exam_select", "value"),
+    ],
+)
+def update_scores_store(exam):
+    if not exam:
+        return [[], [], [], {}]
+    exam = pd.DataFrame.from_dict([json.loads(exam)])
+    scores = get_unstack_scores(exam)
+    fixed_columns = [
+        "exercise",
+        "question",
+        "competence",
+        "theme",
+        "comment",
+        "score_rate",
+        "is_leveled",
+    ]
+
+    students = list(get_students_from_exam(exam))
+    columns = fixed_columns + students
+
+    score_color = get_score_colors()
+
+    return [
+        [{"id": c, "name": c} for c in columns],
+        scores.to_dict("records"),
+        highlight_scores(students, score_color),
+        {"headers": True, "data": len(fixed_columns)},
+    ]
+
+
+@app.callback(
+    [
+        Output("final_score_table", "data"),
+    ],
+    [
+        Input("scores_table", "data"),
+    ],
+)
+def update_finale_score_table(scores):
+    scores_df = pd.DataFrame.from_records(scores)
+    stacked_scores = stack_scores(scores_df)
+    return score_to_final_mark(stacked_scores)
+
+
+@app.callback(
+    [
+        Output("score_statistics_table", "columns"),
+        Output("score_statistics_table", "data"),
+    ],
+    [
+        Input("final_score_table", "data"),
+    ],
+)
+def update_statictics_table(finale_score):
+    df = pd.DataFrame.from_records(finale_score)
+    statistics = df["mark"].describe().to_frame().T
+    return [
+        [{"id": c, "name": c} for c in statistics.columns],
+        statistics.to_dict("records"),
+    ]
+
+
+@app.callback(
+    [
+        Output("fig_exam_histo", "figure"),
+    ],
+    [
+        Input("final_score_table", "data"),
+    ],
+)
+def update_exam_histo(finale_scores):
+    scores = pd.DataFrame.from_records(finale_scores)
+
+    if scores.empty:
+        return [go.Figure(data=[go.Scatter(x=[], y=[])])]
+
+    ranges = np.linspace(
+        -0.5,
+        scores["score_rate"].max(),
+        int(scores["score_rate"].max() * 2 + 2),
+    )
+
+    bins = pd.cut(scores["mark"], ranges)
+    scores["Bin"] = bins
+    grouped = (
+        scores.reset_index()
+        .groupby("Bin")
+        .agg({"score_rate": "count", "student_name": lambda x: "\n".join(x)})
+    )
+    grouped.index = grouped.index.map(lambda i: i.right)
+    fig = go.Figure()
+    fig.add_bar(
+        x=grouped.index,
+        y=grouped["score_rate"],
+        text=grouped["student_name"],
+        textposition="auto",
+        hovertemplate="",
+        marker_color="#4E89DE",
+    )
+    fig.update_layout(
+        height=300,
+        margin=dict(l=5, r=5, b=5, t=5),
+    )
+    return [fig]
+
+
+@app.callback(
+    [
+        Output("fig_questions_bar", "figure"),
+    ],
+    [
+        Input("scores_table", "data"),
+    ],
+)
+def update_questions_bar(finale_scores):
+    scores = pd.DataFrame.from_records(finale_scores)
+    scores = stack_scores(scores)
+
+    if scores.empty:
+        return [go.Figure(data=[go.Scatter(x=[], y=[])])]
+
+    pt = pivot_score_on(scores, ["exercise", "question", "comment"], "score")
+
+    # separation  between exercises
+    for i in {i for i in pt.index.get_level_values(0)}:
+        pt.loc[(str(i), "", ""), :] = ""
+    pt.sort_index(inplace=True)
+
+    # Bar label
+    index = (
+        pt.index.get_level_values(0).map(str)
+        + ":"
+        + pt.index.get_level_values(1).map(str)
+        + " "
+        + pt.index.get_level_values(2).map(str)
+    )
+
+    fig = go.Figure()
+
+    bars = get_level_color_bar()
+
+    for b in bars:
+        try:
+            fig.add_bar(
+                x=index, y=pt[b["score"]], name=b["name"], marker_color=b["color"]
+            )
+        except KeyError:
+            pass
+    fig.update_layout(barmode="relative")
+    fig.update_layout(
+        height=500,
+        margin=dict(l=5, r=5, b=5, t=5),
+        legend=dict(
+            orientation="h",
+            yanchor="bottom",
+            y=1.02,
+            xanchor="right",
+            x=1
+            )
+        )
+    return [fig]

recopytex/dashboard/pages/exams_scores/models.py

@@ -0,0 +1,128 @@
+#!/use/bin/env python
+# encoding: utf-8
+
+from recopytex.database.filesystem.loader import CSVLoader
+from recopytex.datalib.dataframe import column_values_to_column
+import recopytex.datalib.on_score_column as on_column
+import pandas as pd
+
+LOADER = CSVLoader("./test_confia.ml")
+SCORES_CONFIG = LOADER.get_config()["scores"]
+
+
+def unstack_scores(scores):
+    """Put student_name values to columns
+
+    :param scores: Score dataframe with one line per score
+    :returns: Scrore dataframe with student_name in columns
+
+    """
+    kept_columns = [col for col in LOADER.score_columns if col != "score"]
+    return column_values_to_column("student_name", "score", kept_columns, scores)
+
+
+def stack_scores(scores):
+    """Student columns are melt to rows with student_name column
+
+    :param scores: Score dataframe with student_name in columns
+    :returns: Scrore dataframe with one line per score
+
+    """
+    kept_columns = [
+        c for c in LOADER.score_columns if c not in ["score", "student_name"]
+    ]
+    student_names = [c for c in scores.columns if c not in kept_columns]
+    return pd.melt(
+        scores,
+        id_vars=kept_columns,
+        value_vars=student_names,
+        var_name="student_name",
+        value_name="score",
+    )
+
+
+def get_tribes():
+    return LOADER.get_tribes()
+
+
+def get_exams(tribe):
+    return LOADER.get_exams([tribe])
+
+
+def get_record_scores(exam):
+    return LOADER.get_exam_scores(exam)
+
+
+def get_unstack_scores(exam):
+    flat_scores = LOADER.get_exam_scores(exam)
+    return unstack_scores(flat_scores)
+
+
+def get_students_from_exam(exam):
+    flat_scores = LOADER.get_exam_scores(exam)
+    return flat_scores["student_name"].unique()
+
+
+def get_score_colors():
+    score_color = {}
+    for key, score in SCORES_CONFIG.items():
+        score_color[score["value"]] = score["color"]
+    return score_color
+
+
+def get_level_color_bar():
+    return [
+        {"score": str(s["value"]), "name": s["comment"], "color": s["color"]}
+        for s in SCORES_CONFIG.values()
+    ]
+
+
+is_none_score = lambda x: on_column.is_none_score(x, SCORES_CONFIG)
+format_score = lambda x: on_column.format_score(x, SCORES_CONFIG)
+score_to_numeric_score = lambda x: on_column.score_to_numeric_score(x, SCORES_CONFIG)
+score_to_mark = lambda x: on_column.score_to_mark(
+    x, max([v["value"] for v in SCORES_CONFIG.values() if isinstance(v["value"], int)])
+)
+
+
+def filter_clean_score(scores):
+    filtered_scores = scores[~scores.apply(is_none_score, axis=1)]
+    filtered_scores = filtered_scores.assign(
+        score=filtered_scores.apply(format_score, axis=1)
+    )
+    return filtered_scores
+
+
+def score_to_final_mark(scores):
+    """ Compute marks then reduce to final mark per student """
+
+    filtered_scores = filter_clean_score(scores)
+    filtered_scores = filtered_scores.assign(
+        score=filtered_scores.apply(score_to_numeric_score, axis=1)
+    )
+    filtered_scores = filtered_scores.assign(
+        mark=filtered_scores.apply(score_to_mark, axis=1)
+    )
+    final_score = filtered_scores.groupby(["student_name"])[
+        ["mark", "score_rate"]
+    ].sum()
+    return [final_score.reset_index().to_dict("records")]
+
+
+def pivot_score_on(scores, index, columns, aggfunc="size"):
+    """Pivot scores on index, columns with aggfunc
+
+    It assumes thant scores are levels
+
+    """
+    filtered_scores = filter_clean_score(scores)
+    filtered_scores["score"] = filtered_scores["score"].astype(str)
+    pt = pd.pivot_table(
+        filtered_scores,
+        index=index,
+        columns=columns,
+        aggfunc=aggfunc,
+        fill_value=0,
+    )
+    return pt
+

recopytex/dashboard/pages/home/app.py

@@ -0,0 +1,50 @@
+#!/usr/bin/env python
+# encoding: utf-8
+
+import dash_html_components as html
+from recopytex.database.filesystem.loader import CSVLoader
+from .models import get_tribes, get_exams, get_students
+
+loader = CSVLoader("./test_config.yml")
+
+
+def listing(elements, formating=lambda x: x):
+
+    return html.Ul(
+        children=[html.Li(children=formating(element)) for element in elements]
+    )
+
+
+def format_tribe(tribe):
+    children = [html.H3(tribe["name"])]
+    exams = loader.get_exams([tribe["name"]])
+    if exams.empty:
+        children.append(html.P("Pas d'évaluation"))
+    else:
+        exams_html = listing([exam for id, exam in exams.iterrows()], format_exam)
+        children.append(exams_html)
+    return children
+
+
+def format_exam(exam):
+    children = [html.P(exam["name"])]
+    return children
+
+
+layout = html.Div(
+    children=[
+        html.H1("Recopytex"),
+        html.H2("Tribes"),
+        html.Div(
+            children=[listing(loader.get_tribes().values(), format_tribe)],
+            id="tribes",
+        ),
+        html.H2("Config"),
+        html.Div(
+            children=[
+                html.P(str(loader.get_config())),
+            ],
+            id="config",
+        ),
+    ]
+)

recopytex/dashboard/pages/home/callbacks.py

@@ -0,0 +1,6 @@
+#!/usr/bin/env python
+# encoding: utf-8
+
+from dash.dependencies import Input, Output
+from recopytex.dashboard.app import app
+

recopytex/dashboard/pages/home/models.py

@@ -0,0 +1,14 @@
+#!/usr/bin/env python
+# encoding: utf-8
+
+
+def get_tribes(loader):
+    return loader.get_tribes()
+
+
+def get_exams(loader, tribe):
+    return loader.get_exams([tribe])
+
+
+def get_students(loader, tribe):
+    return loader.get_students([tribe])

recopytex/dashboard/routes.py

@@ -0,0 +1,27 @@
+#!/usr/bin/env python
+# encoding: utf-8
+
+from dash.dependencies import Input, Output
+
+from .app import app
+from .pages.home import app as home
+from .pages.exams_scores import app as exams_scores
+import dash_html_components as html
+
+
+@app.callback(Output("page-content", "children"), [Input("url", "pathname")])
+def render_page_content(pathname):
+    if pathname == "/":
+        return home.layout
+    elif pathname == "/exams/scores/":
+        return exams_scores.layout
+    # elif pathname == iris_page_location:
+    #     return iris.layout
+    # # If the user tries to reach a different page, return a 404 message
+    return html.Div(
+        [
+            html.H1("404: Not found", className="text-danger"),
+            html.Hr(),
+            html.P(f"The pathname {pathname} was not recognised..."),
+        ]
+    )

recopytex/database/__init__.py

@@ -0,0 +1,88 @@
+#!/usr/bin/env python
+# encoding: utf-8
+
+from abc import ABC, abstractmethod
+import yaml
+
+"""
+
+Adapter to pull data from the filesystem
+
+# Loader
+
+# Writer
+"""
+
+
+class Loader(ABC):
+
+    """Load data from source"""
+
+    CONFIG = {}
+
+    def __init__(self, configfile=""):
+        """Init loader
+
+        :param configfile: yaml file with informations on data source
+        """
+        self._config = self.CONFIG
+        if configfile.endswith(".yml"):
+            with open(configfile, "r") as config:
+                self._config.update(yaml.load(config, Loader=yaml.FullLoader))
+
+    def get_config(self):
+        """ Get config"""
+        return self._config
+
+    @abstractmethod
+    def get_tribes(self):
+        """ Get tribes list """
+        pass
+
+    @abstractmethod
+    def get_exams(self, tribes=[]):
+        """Get exams list
+
+        :param tribes: get only exams for those tribes
+        """
+        pass
+
+    @abstractmethod
+    def get_students(self, tribes=[]):
+        """Get student list
+
+        :param filters: list of filters
+        """
+        pass
+
+    @abstractmethod
+    def get_exam_questions(self, exams=[]):
+        """Get questions for the exam
+
+        :param exams: questions for those exams only
+        """
+        pass
+
+    @abstractmethod
+    def get_questions_scores(self, questions=[]):
+        """Get scores of those questions
+
+        :param questions: score for those questions
+        """
+        pass
+
+    # @abstractmethod
+    # def get_student_scores(self, student):
+    #     """Get scores of the student
+
+    #     :param student:
+    #     """
+    #     pass
+
+
+class Writer(ABC):
+
+    """ Write datas to the source """
+
+    def __init__(self):
+        pass

recopytex/database/filesystem/__init__.py

@@ -0,0 +1,15 @@
+#!/usr/bin/env python
+# encoding: utf-8
+
+"""
+Store data using filesystem for organisation, csv for scores
+
+## Organisation
+
+- tribe1.csv # list of students for the tribe
+- tribe1/
+    - exam1.csv # questions and scores for exam1
+    - exam1.yml # Extra information about exam1
+    - exam2.csv # questions and scores for exam2
+"""
+

recopytex/database/filesystem/default_config.yml

@@ -0,0 +1,75 @@
+---
+source: ./ # basepath where to start 
+
+competences: # Competences 
+  Chercher:
+    name: Chercher
+    abrv: Cher
+  Représenter:
+    name: Représenter
+    abrv: Rep
+  Modéliser:
+    name: Modéliser
+    abrv: Mod
+  Raisonner:
+    name: Raisonner
+    abrv: Rai
+  Calculer:
+    name: Calculer
+    abrv: Cal
+  Communiquer:
+    name: Communiquer
+    abrv: Com
+
+scores: # 
+  BAD: # Everything is bad
+    value: 0 
+    numeric_value: 0 
+    color: "#E7472B"
+    comment: Faux
+  FEW: # Few good things
+    value: 1 
+    numeric_value: 1 
+    color: "#FF712B"
+    comment: Peu juste
+  NEARLY: # Nearly good but things are missing
+    value: 2
+    numeric_value: 2
+    color: "#F2EC4C"
+    comment: Presque juste
+  GOOD: # Everything is good
+    value: 3
+    numeric_value: 3
+    color: "#68D42F"
+    comment: Juste
+  NOTFILLED: # The item is not scored yet
+    value: ""
+    numeric_value: None
+    color: white
+    comment: En attente
+  NOANSWER: # Student gives no answer (count as 0)
+    value: "."
+    numeric_value: 0
+    color: black
+    comment: Pas de réponse
+  ABS: # Student has absent (this score won't be impact the final mark)
+    value: a
+    numeric_value: None
+    color: lightgray
+    comment: Non noté
+
+csv_fields: # dataframe_field: csv_field 
+  term: Trimestre
+  exam: Nom
+  date: Date
+  exercise: Exercice
+  question: Question
+  competence: Competence
+  theme: Domaine
+  comment: Commentaire
+  score_rate: Bareme
+  is_leveled: Est_nivele
+
+id_templates:
+    exam: "{name}_{tribe}"
+    question: "{exam_id}_{exercise}_{question}_{comment}"

recopytex/database/filesystem/lib.py

@@ -0,0 +1,52 @@
+#!/usr/bin/env python
+# encoding: utf-8
+
+import pandas as pd
+from pathlib import Path
+from unidecode import unidecode
+
+
+__all__ = ["list_csvs", "extract_fields"]
+
+
+def list_csvs(path):
+    """list csv files in path
+
+    :example:
+    >>> list_csvs("./example/Tribe1/")
+    [PosixPath('example/Tribe1/210112_DS.csv'), PosixPath('example/Tribe1/210122_DS6.csv')]
+    >>> list_csvs("./example/Tribe1")
+    [PosixPath('example/Tribe1/210112_DS.csv'), PosixPath('example/Tribe1/210122_DS6.csv')]
+    """
+    return list(Path(path).glob("*.csv"))
+
+
+def extract_fields(csv_filename, fields=[], remove_duplicates=True):
+    """Extract fields in csv
+
+    :param csv_filename: csv filename (with header)
+    :param fields: list of fields to extract (all fields if empty list - default)
+    :param remove_duplicates: keep uniques rows (default True)
+
+    :example:
+    >>> extract_fields("./example/Tribe1/210122_DS6.csv", ["Trimestre", "Nom", "Date"])
+       Trimestre  Nom        Date
+    0          1  DS6  22/01/2021
+    """
+    df = pd.read_csv(csv_filename)
+    if fields:
+        df = df[fields]
+    if remove_duplicates:
+        return df.drop_duplicates()
+    return df
+
+
+def build_id(template, element):
+    """Build an id from template to the element
+
+    :example:
+    >>> element = {"name": "pléà", "place": "here", "foo":"bar"}
+    >>> build_id("{name} {place}", element)
+    'plea_here'
+    """
+    return unidecode(template.format(**element)).replace(" ", "_")

recopytex/database/filesystem/loader.py

@@ -0,0 +1,298 @@
+#!/usr/bin/env python
+# encoding: utf-8
+
+import yaml
+import os
+import uuid
+from pathlib import Path
+import pandas as pd
+from .. import Loader
+from .lib import list_csvs, extract_fields, build_id
+
+
+DEFAULT_CONFIG_FILE = os.path.join(os.path.dirname(__file__), "default_config.yml")
+with open(DEFAULT_CONFIG_FILE, "r") as config:
+    DEFAULT_CONFIG = yaml.load(config, Loader=yaml.FullLoader)
+
+
+def maybe_dataframe(datas):
+    try:
+        return [e[1] for e in datas.iterrows()]
+    except AttributeError:
+        return datas
+
+
+class CSVLoader(Loader):
+
+    """Loader when scores and metadatas are stored in csv files
+
+    :config:
+
+    :example:
+    >>> loader = CSVLoader()
+    >>> loader.get_config()
+    {'source': './', 'competences': {'Chercher': {'name': 'Chercher', 'abrv': 'Cher'}, 'Représenter': {'name': 'Représenter', 'abrv': 'Rep'}, 'Modéliser': {'name': 'Modéliser', 'abrv': 'Mod'}, 'Raisonner': {'name': 'Raisonner', 'abrv': 'Rai'}, 'Calculer': {'name': 'Calculer', 'abrv': 'Cal'}, 'Communiquer': {'name': 'Communiquer', 'abrv': 'Com'}}, 'scores': {'BAD': {'value': 0, 'numeric_value': 0, 'color': '#E7472B', 'comment': 'Faux'}, 'FEW': {'value': 1, 'numeric_value': 1, 'color': '#FF712B', 'comment': 'Peu juste'}, 'NEARLY': {'value': 2, 'numeric_value': 2, 'color': '#F2EC4C', 'comment': 'Presque juste'}, 'GOOD': {'value': 3, 'numeric_value': 3, 'color': '#68D42F', 'comment': 'Juste'}, 'NOTFILLED': {'value': '', 'numeric_value': 'None', 'color': 'white', 'comment': 'En attente'}, 'NOANSWER': {'value': '.', 'numeric_value': 0, 'color': 'black', 'comment': 'Pas de réponse'}, 'ABS': {'value': 'a', 'numeric_value': 'None', 'color': 'lightgray', 'comment': 'Non noté'}}, 'csv_fields': {'term': 'Trimestre', 'exam': 'Nom', 'date': 'Date', 'exercise': 'Exercice', 'question': 'Question', 'competence': 'Competence', 'theme': 'Domaine', 'comment': 'Commentaire', 'score_rate': 'Bareme', 'is_leveled': 'Est_nivele'}, 'id_templates': {'exam': '{name}_{tribe}', 'question': '{exam_id}_{exercise}_{question}_{comment}'}}
+
+    >>> loader = CSVLoader("./test_config.yml")
+    >>> loader.get_config()
+    {'source': './example', 'competences': {'Chercher': {'name': 'Chercher', 'abrv': 'Cher'}, 'Représenter': {'name': 'Représenter', 'abrv': 'Rep'}, 'Modéliser': {'name': 'Modéliser', 'abrv': 'Mod'}, 'Raisonner': {'name': 'Raisonner', 'abrv': 'Rai'}, 'Calculer': {'name': 'Calculer', 'abrv': 'Cal'}, 'Communiquer': {'name': 'Communiquer', 'abrv': 'Com'}}, 'scores': {'BAD': {'value': 0, 'numeric_value': 0, 'color': '#E7472B', 'comment': 'Faux'}, 'FEW': {'value': 1, 'numeric_value': 1, 'color': '#FF712B', 'comment': 'Peu juste'}, 'NEARLY': {'value': 2, 'numeric_value': 2, 'color': '#F2EC4C', 'comment': 'Presque juste'}, 'GOOD': {'value': 3, 'numeric_value': 3, 'color': '#68D42F', 'comment': 'Juste'}, 'NOTFILLED': {'value': '', 'numeric_value': 'None', 'color': 'white', 'comment': 'En attente'}, 'NOANSWER': {'value': '.', 'numeric_value': 0, 'color': 'black', 'comment': 'Pas de réponse'}, 'ABS': {'value': 'a', 'numeric_value': 'None', 'color': 'lightgray', 'comment': 'Non noté'}}, 'csv_fields': {'term': 'Trimestre', 'exam': 'Nom', 'date': 'Date', 'exercise': 'Exercice', 'question': 'Question', 'competence': 'Competence', 'theme': 'Domaine', 'comment': 'Commentaire', 'score_rate': 'Bareme', 'is_leveled': 'Est_nivele'}, 'id_templates': {'exam': '{name}_{tribe}', 'question': '{exam_id}_{exercise}_{question}_{comment}'}, 'output': './output', 'templates': 'templates/', 'tribes': {'Tribe1': {'name': 'Tribe1', 'type': 'Type1', 'students': 'tribe1.csv'}, 'Tribe2': {'name': 'Tribe2', 'students': 'tribe2.csv'}}}
+    """
+
+    CONFIG = DEFAULT_CONFIG
+
+    def get_config(self):
+        """ Get config """
+        return self._config
+
+    @property
+    def exam_columns(self):
+        return pd.Index(["name", "date", "term", "origin", "tribe", "id"])
+
+    @property
+    def question_columns(self):
+        return pd.Index(
+            [
+                "exercise",
+                "question",
+                "competence",
+                "theme",
+                "comment",
+                "score_rate",
+                "is_leveled",
+                "origin",
+                "exam_id",
+                "id",
+            ]
+        )
+
+    @property
+    def score_columns(self):
+        return pd.Index(
+            [
+                "term",
+                "exam",
+                "date",
+                "exercise",
+                "question",
+                "competence",
+                "theme",
+                "comment",
+                "score_rate",
+                "is_leveled",
+                "origin",
+                "exam_id",
+                "question_id",
+                "student_name",
+                "score",
+            ]
+        )
+
+    def rename_columns(self, dataframe):
+        """Rename dataframe column to match with `csv_fields`
+
+        :param dataframe: the dataframe
+
+        :example:
+        >>> loader = CSVLoader()
+        >>>
+
+        """
+        return dataframe.rename(
+            columns={v: k for k, v in self._config["csv_fields"].items()}
+        )
+
+    def reverse_csv_field(self, keys):
+        """ Reverse csv field from keys """
+        return [self._config["csv_fields"][k] for k in keys]
+
+    def get_tribes(self, only_names=False):
+        """Get tribes list
+
+        :example:
+        >>> loader = CSVLoader("./test_config.yml")
+        >>> loader.get_tribes()
+        {'Tribe1': {'name': 'Tribe1', 'type': 'Type1', 'students': 'tribe1.csv'}, 'Tribe2': {'name': 'Tribe2', 'students': 'tribe2.csv'}}
+        >>> loader.get_tribes(only_names=True)
+        ['Tribe1', 'Tribe2']
+        """
+        if only_names:
+            return list(self._config["tribes"].keys())
+        return self._config["tribes"]
+
+    def get_exams(self, tribes=[]):
+        """Get exams list
+
+        :param tribes: get only exams for those tribes
+        :return: dataframe of exams
+
+        :example:
+        >>> loader = CSVLoader("./test_config.yml")
+        >>> exams = loader.get_exams(["Tribe1"])
+        >>> all(exams.columns == loader.exam_columns)
+        True
+        >>> exams
+          name        date  term                         origin   tribe          id
+        0   DS  12/01/2021     1   example/Tribe1/210112_DS.csv  Tribe1   DS_Tribe1
+        0  DS6  22/01/2021     1  example/Tribe1/210122_DS6.csv  Tribe1  DS6_Tribe1
+        """
+        exams = []
+        for tribe in tribes:
+            tribe_path = Path(self._config["source"]) / tribe
+            csvs = list_csvs(tribe_path)
+            for csv in csvs:
+                fields = self.reverse_csv_field(["exam", "date", "term"])
+                exam = extract_fields(csv, fields)
+                exam = self.rename_columns(exam)
+                exam = exam.rename(columns={"exam": "name"})
+                exam["origin"] = str(csv)
+                exam["tribe"] = tribe
+                exam["id"] = build_id(
+                    self._config["id_templates"]["exam"], exam.iloc[0]
+                )
+                exams.append(exam)
+        if exams:
+            return pd.concat(exams)
+        return pd.DataFrame(columns=["name", "date", "term", "origin", "tribe", "id"])
+
+    def get_exam_questions(self, exams=[]):
+        """Get questions for exams stored in score_files
+
+        :param exams: list or dataframe of exams metadatas (need origin field to find the csv)
+
+        :example:
+        >>> loader = CSVLoader("./test_config.yml")
+        >>> exams = loader.get_exams(["Tribe1"])
+        >>> all(loader.get_exam_questions([exams.iloc[0]]).columns == loader.question_columns)
+        True
+        >>> questions = loader.get_exam_questions(exams)
+        >>> questions.iloc[0]
+        exercise                         Exercice 1
+        question                                  1
+        competence                         Calculer
+        theme                                  Plop
+        comment                              Coucou
+        score_rate                              1.0
+        is_leveled                              1.0
+        origin         example/Tribe1/210112_DS.csv
+        exam_id                           DS_Tribe1
+        id            DS_Tribe1_Exercice_1_1_Coucou
+        Name: 0, dtype: object
+        """
+        _exams = maybe_dataframe(exams)
+
+        questions = []
+        for exam in _exams:
+            fields = self.reverse_csv_field(
+                [
+                    "exercise",
+                    "question",
+                    "competence",
+                    "theme",
+                    "comment",
+                    "score_rate",
+                    "is_leveled",
+                ]
+            )
+            question = extract_fields(exam["origin"], fields)
+            question = self.rename_columns(question)
+            question["origin"] = exam["origin"]
+            question["exam_id"] = exam["id"]
+            question["id"] = build_id(
+                self._config["id_templates"]["question"], question.iloc[0]
+            )
+            questions.append(question)
+
+        return pd.concat(questions)
+
+    def get_questions_scores(self, questions=[]):
+        """Get scores of those questions
+
+        :param questions: list or dataframe of questions metadatas (need origin field to find the csv)
+
+        :example:
+        >>> loader = CSVLoader("./test_config.yml")
+        >>> exams = loader.get_exams(["Tribe1"])
+        >>> questions = loader.get_exam_questions(exams)
+        >>> scores = loader.get_questions_scores(questions)
+        >>> all(scores.columns == loader.score_columns)
+        True
+        >>> scores["student_name"].unique()
+        array(['Star Tice', 'Umberto Dingate', 'Starlin Crangle',
+               'Humbert Bourcq', 'Gabriella Handyside', 'Stewart Eaves',
+               'Erick Going', 'Ase Praton', 'Rollins Planks', 'Dunstan Sarjant',
+               'Stacy Guiton', 'Ange Stanes', 'Amabelle Elleton',
+               'Darn Broomhall', 'Dyan Chatto', 'Keane Rennebach', 'Nari Paulton',
+               'Brandy Wase', 'Jaclyn Firidolfi', 'Violette Lockney'],
+              dtype=object)
+        """
+        scores = []
+        group_questions = questions.groupby("origin")
+        for origin, questions_df in group_questions:
+            scores_df = pd.read_csv(origin)
+            scores_df = self.rename_columns(scores_df)
+            student_names = [
+                c
+                for c in scores_df.columns
+                if c not in self._config["csv_fields"].keys()
+            ]
+
+            common_columns = [c for c in questions_df.columns if c in scores_df.columns]
+            scores_df = pd.merge(scores_df, questions_df, on=common_columns)
+
+            kept_columns = [c for c in scores_df if c not in student_names]
+            scores_df = pd.melt(
+                scores_df,
+                id_vars=kept_columns,
+                value_vars=student_names,
+                var_name="student_name",
+                value_name="score",
+            )
+
+            scores_df = scores_df.rename(columns={"id": "question_id"})
+            scores.append(scores_df)
+
+        return pd.concat(scores)
+
+    def get_exam_scores(self, exams=[]):
+        """Get scores for all question of the exam
+
+        :param exams: list or dataframe of exams metadatas (need origin field to find the csv)
+
+        :example:
+        >>> loader = CSVLoader("./test_config.yml")
+        >>> exams = loader.get_exams(["Tribe1"])
+        >>> scores = loader.get_exam_scores(exams)
+        >>> scores.columns
+        Index(['term', 'exam', 'date', 'exercise', 'question', 'competence', 'theme',
+               'comment', 'score_rate', 'is_leveled', 'origin', 'exam_id',
+               'question_id', 'student_name', 'score'],
+              dtype='object')
+        """
+        questions = self.get_exam_questions(exams)
+        return self.get_questions_scores(questions)
+
+    def get_students(self, tribes=[]):
+        """Get student list
+
+        :param tribes: concerned tribes
+
+        :example:
+        >>> loader = CSVLoader("./test_config.yml")
+        >>> tribes = loader.get_tribes()
+        >>> students = loader.get_students([tribes["Tribe1"]])
+        >>> students.columns
+        Index(['Nom', 'email', 'origin', 'tribe'], dtype='object')
+        """
+        students = []
+        for tribe in tribes:
+            students_csv = Path(self._config["source"]) / tribe["students"]
+            students_df = pd.read_csv(students_csv)
+            students_df["origin"] = students_csv
+            students_df["tribe"] = tribe["name"]
+            students.append(students_df)
+
+        return pd.concat(students)
+
+    def get_student_scores(self, student=[]):
+        """Get all scores for students"""
+        pass

recopytex/database/filesystem/writer.py

@@ -0,0 +1,7 @@
+#!/usr/bin/env python
+# encoding: utf-8
+
+"""
+
+"""
+

recopytex/datalib/dataframe.py

@@ -0,0 +1,21 @@
+#!/usr/bin/env python
+# encoding: utf-8
+
+
+def column_values_to_column(pivot_column, value_column, kept_columns, df):
+    """Pivot_column's values go to column with value_column under it, keeping kept_columns
+
+    :param pivot_column: column name where value will become columns
+    :param value_column: column name where value will be under pivot_column
+    :param kept_columns: unchanged columns
+    :param df: DataFrame to work with
+
+    :return: Stack dataframe
+
+    """
+    if pivot_column in kept_columns:
+        pivot_columns = kept_columns
+    else:
+        pivot_columns = kept_columns + [pivot_column]
+
+    return df.set_index(pivot_columns).unstack(pivot_column)[value_column].reset_index()

recopytex/datalib/on_score_column.py

@@ -0,0 +1,257 @@
+#!/usr/bin/env python
+# encoding: utf-8
+
+from math import ceil
+import pandas as pd
+
+
+def is_none_score(x, score_config):
+    """Is a score correspond to a None numeric_value which
+
+    >>> import pandas as pd
+    >>> 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.apply(lambda x:is_none_score(x, score_config), axis=1)
+    0    False
+    1     True
+    2    False
+    3     True
+    4    False
+    5    False
+    6    False
+    dtype: bool
+
+    """
+    none_values = [
+        v["value"]
+        for v in score_config.values()
+        if str(v["numeric_value"]).lower() == "none"
+    ]
+    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
+
+    >>> import pandas as pd
+    >>> 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.apply(lambda x:score_to_numeric_score(x, score_config), axis=1)
+    0    0.33
+    1    None
+    2       0
+    3    None
+    4       1
+    5       2
+    6       3
+    dtype: object
+
+    """
+    if x["is_leveled"]:
+        replacements = {v["value"]: v["numeric_value"] for v in score_config.values()}
+        return replacements[x["score"]]
+
+    return x["score"]
+
+
+def score_to_mark(x, score_max, rounding=lambda x: round(x, 2)):
+    """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
+
+    :param x: dictionnary with "is_leveled", "score"  (need to be number) and "score_rate" keys
+    :param score_max:
+    :param rounding: rounding mark function
+    :return: the mark
+
+    >>> import pandas as pd
+    >>> 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 = 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
+    >>> 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)):
+            raise ValueError(f"The evaluation is out of range: {x['score']} at {x}")
+        return rounding(x["score"] * x["score_rate"] / score_max)
+
+    return rounding(x["score"])
+
+
+def score_to_level(x, level_max=3):
+    """Compute the level (".",0,1,2,3).
+
+    :param x: dictionnary with "is_leveled", "score" and "score_rate" keys
+    :return: the level
+
+    >>> 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, 0, 1.5, 1, 3,   0.666, 1, 1.5, 1, 2, 3],
+    ...    }
+    >>> df = pd.DataFrame(d)
+    >>> df
+       Eleve  score_rate  is_leveled  score
+    0     E1           1           0  1.000
+    1     E1           1           0  0.330
+    2     E1           2           0  0.000
+    3     E1           2           0  1.500
+    4     E1           2           1  1.000
+    5     E1           2           1  3.000
+    6     E2           1           0  0.666
+    7     E2           1           0  1.000
+    8     E2           2           0  1.500
+    9     E2           2           0  1.000
+    10    E2           2           1  2.000
+    11    E2           2           1  3.000
+    >>> df.apply(score_to_level, axis=1)
+    0     3
+    1     1
+    2     0
+    3     3
+    4     1
+    5     3
+    6     2
+    7     3
+    8     3
+    9     2
+    10    2
+    11    3
+    dtype: int64
+    >>> df.apply(lambda x: score_to_level(x, 5), axis=1)
+    0     5
+    1     2
+    2     0
+    3     4
+    4     1
+    5     3
+    6     4
+    7     5
+    8     4
+    9     3
+    10    2
+    11    3
+    dtype: int64
+    """
+    if x["is_leveled"]:
+        return int(x["score"])
+
+    if x["score"] > x["score_rate"]:
+        raise ValueError(
+            f"score is higher than score_rate ({x['score']} > {x['score_rate']}) for {x}"
+        )
+
+    return int(ceil(x["score"] / x["score_rate"] * level_max))
+
+
+# -----------------------------
+# Reglages pour 'vim'
+# vim:set autoindent expandtab tabstop=4 shiftwidth=4:
+# cursor: 16 del

recopytex/datalib/on_value.py

@@ -0,0 +1,40 @@
+#!/usr/bin/env python
+# encoding: utf-8
+
+from math import ceil, floor
+
+
+def round_with_base(x, base=0.5):
+    """Round to a multiple of base
+
+    :example:
+    >>> round_with_base(1.33, 0.1)
+    1.3
+    >>> round_with_base(1.33, 0.2)
+    1.4
+    >>> round_with_base(1.33, 1)
+    1
+    >>> round_with_base(1.33, 2)
+    2
+    """
+    try:
+        prec = len(str(base).split(".")[1])
+    except IndexError:
+        prec = 0
+    return round(base * round(float(x) / base), prec)
+
+
+def round_half_point(x):
+    """Round to nearest half point
+
+    :example:
+    >>> round_half_point(1.33)
+    1.5
+    >>> round_half_point(1.1)
+    1.0
+    >>> round_half_point(1.66)
+    1.5
+    >>> round_half_point(1.76)
+    2.0
+    """
+    return round_with_base(x, base=0.5)

recopytex/df_marks_manip.py

@@ -1,205 +0,0 @@
-#!/usr/bin/env python
-# encoding: utf-8
-
-import pandas as pd
-import numpy as np
-from math import ceil, floor
-from .config import COLUMNS, VALIDSCORE
-
-# Values manipulations
-
-
-def round_half_point(val):
-    try:
-        return 0.5 * ceil(2.0 * val)
-    except ValueError:
-        return val
-    except TypeError:
-        return val
-
-
-def score_to_mark(x):
-    """ Compute the mark
-
-    if the item is leveled then the score is multiply by the score_rate
-    otherwise it copies the score
-
-    :param x: dictionnary with COLUMNS["is_leveled"], COLUMNS["score"] and COLUMNS["score_rate"] keys
-
-    >>> d = {"Eleve":["E1"]*6 + ["E2"]*6,
-    ...    COLUMNS["score_rate"]:[1]*2+[2]*2+[2]*2 + [1]*2+[2]*2+[2]*2,
-    ...    COLUMNS["is_leveled"]:[0]*4+[1]*2 + [0]*4+[1]*2,
-    ...    COLUMNS["score"]:[1, 0.33, 2, 1.5, 1, 3,   0.666, 1, 1.5, 1, 2, 3],
-    ...    }
-    >>> df = pd.DataFrame(d)
-    >>> score_to_mark(df.loc[0])
-    1.0
-    >>> score_to_mark(df.loc[10])
-    1.3333333333333333
-    """
-    # -1 is no answer
-    if x[COLUMNS["score"]] == -1:
-        return 0
-
-    if x[COLUMNS["is_leveled"]]:
-        if x[COLUMNS["score"]] not in [0, 1, 2, 3]:
-            raise ValueError(f"The evaluation is out of range: {x[COLUMNS['score']]} at {x}")
-        return round_half_point(x[COLUMNS["score"]] * x[COLUMNS["score_rate"]] / 3)
-
-    if x[COLUMNS["score"]] > x[COLUMNS["score_rate"]]:
-        raise ValueError(
-            f"The score ({x['score']}) is greated than the rating scale ({x[COLUMNS['score_rate']]}) at {x}"
-        )
-    return x[COLUMNS["score"]]
-
-
-def score_to_level(x):
-    """ Compute the level (".",0,1,2,3).
-
-    :param x: dictionnary with COLUMNS["is_leveled"], COLUMNS["score"] and COLUMNS["score_rate"] keys
-
-    >>> d = {"Eleve":["E1"]*6 + ["E2"]*6,
-    ...    COLUMNS["score_rate"]:[1]*2+[2]*2+[2]*2 + [1]*2+[2]*2+[2]*2,
-    ...    COLUMNS["is_leveled"]:[0]*4+[1]*2 + [0]*4+[1]*2,
-    ...    COLUMNS["score"]:[1, 0.33, np.nan, 1.5, 1, 3,   0.666, 1, 1.5, 1, 2, 3],
-    ...    }
-    >>> df = pd.DataFrame(d)
-    >>> score_to_level(df.loc[0])
-    3
-    >>> score_to_level(df.loc[1])
-    1
-    >>> score_to_level(df.loc[2])
-    'na'
-    >>> score_to_level(df.loc[3])
-    3
-    >>> score_to_level(df.loc[5])
-    3
-    >>> score_to_level(df.loc[10])
-    2
-    """
-    # negatives are no answer or negatives points
-    if x[COLUMNS["score"]] <= -1:
-        return np.nan
-
-    if x[COLUMNS["is_leveled"]]:
-        return int(x[COLUMNS["score"]])
-
-    return int(ceil(x[COLUMNS["score"]] / x[COLUMNS["score_rate"]] * 3))
-
-
-# DataFrame columns manipulations
-
-
-def compute_mark(df):
-    """ Add Mark column to df
-
-    :param df: DataFrame with COLUMNS["score"], COLUMNS["is_leveled"] and COLUMNS["score_rate"] columns.
-
-    >>> d = {"Eleve":["E1"]*6 + ["E2"]*6,
-    ...    COLUMNS["score_rate"]:[1]*2+[2]*2+[2]*2 + [1]*2+[2]*2+[2]*2,
-    ...    COLUMNS["is_leveled"]:[0]*4+[1]*2 + [0]*4+[1]*2,
-    ...    COLUMNS["score"]:[1, 0.33, 2, 1.5, 1, 3,   0.666, 1, 1.5, 1, 2, 3],
-    ...    }
-    >>> df = pd.DataFrame(d)
-    >>> compute_mark(df)
-    0     1.00
-    1     0.33
-    2     2.00
-    3     1.50
-    4     0.67
-    5     2.00
-    6     0.67
-    7     1.00
-    8     1.50
-    9     1.00
-    10    1.33
-    11    2.00
-    dtype: float64
-    """
-    return df[[COLUMNS["score"], COLUMNS["is_leveled"], COLUMNS["score_rate"]]].apply(
-        score_to_mark, axis=1
-    )
-
-
-def compute_level(df):
-    """ Add Mark column to df
-
-    :param df: DataFrame with COLUMNS["score"], COLUMNS["is_leveled"] and COLUMNS["score_rate"] columns.
-
-    >>> d = {"Eleve":["E1"]*6 + ["E2"]*6,
-    ...    COLUMNS["score_rate"]:[1]*2+[2]*2+[2]*2 + [1]*2+[2]*2+[2]*2,
-    ...    COLUMNS["is_leveled"]:[0]*4+[1]*2 + [0]*4+[1]*2,
-    ...    COLUMNS["score"]:[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[[COLUMNS["score"], COLUMNS["is_leveled"], COLUMNS["score_rate"]]].apply(
-        score_to_level, axis=1
-    )
-
-
-def compute_normalized(df):
-    """ Compute the normalized mark (Mark / score_rate)
-
-    :param df: DataFrame with "Mark" and COLUMNS["score_rate"] columns
-
-    >>> d = {"Eleve":["E1"]*6 + ["E2"]*6,
-    ...    COLUMNS["score_rate"]:[1]*2+[2]*2+[2]*2 + [1]*2+[2]*2+[2]*2,
-    ...    COLUMNS["is_leveled"]:[0]*4+[1]*2 + [0]*4+[1]*2,
-    ...    COLUMNS["score"]:[1, 0.33, 2, 1.5, 1, 3,   0.666, 1, 1.5, 1, 2, 3],
-    ...    }
-    >>> df = pd.DataFrame(d)
-    >>> df["Mark"] = compute_marks(df)
-    >>> compute_normalized(df)
-    0     1.00
-    1     0.33
-    2     1.00
-    3     0.75
-    4     0.33
-    5     1.00
-    6     0.67
-    7     1.00
-    8     0.75
-    9     0.50
-    10    0.67
-    11    1.00
-    dtype: float64
-    """
-    return df[COLUMNS["mark"]] / df[COLUMNS["score_rate"]]
-
-
-# Postprocessing question scores
-
-
-def pp_q_scores(df):
-    """ Postprocessing questions scores dataframe
-
-    :param df: questions-scores dataframe
-    :return: same data frame with mark, level and normalize columns
-    """
-    assign = {
-        COLUMNS["mark"]: compute_mark,
-        COLUMNS["level"]: compute_level,
-        COLUMNS["normalized"]: compute_normalized,
-    }
-    return df.assign(**assign)
-
-
-# -----------------------------
-# Reglages pour 'vim'
-# vim:set autoindent expandtab tabstop=4 shiftwidth=4:
-# cursor: 16 del

recopytex/scripts/recopytex.py

@@ -2,17 +2,7 @@
 # encoding: utf-8
 
 import click
-from pathlib import Path
-import yaml
-import sys
-import papermill as pm
-from datetime import datetime
-
-CONFIGPATH = "recoconfig.yml"
-
-with open(CONFIGPATH, "r") as config:
-    config = yaml.load(config, Loader=yaml.FullLoader)
-
+from recopytex.dashboard.index import app as dash
 
 @click.group()
 def cli():
@@ -20,62 +10,9 @@ def cli():
 
 
 @cli.command()
-def print_config():
-    click.echo(f"Config file is {CONFIGPATH}")
-    click.echo("It contains")
-    click.echo(config)
-
-
-@cli.command()
-@click.argument("csv_file")
-def report(csv_file):
-    csv = Path(csv_file)
-    if not csv.exists():
-        click.echo(f"{csv_file} does not exists")
-        sys.exit(1)
-    if csv.suffix != ".csv":
-        click.echo(f"{csv_file} has to be a csv file")
-        sys.exit(1)
-
-    csv_file = Path(csv_file)
-    tribe_dir = csv_file.parent
-    csv_filename = csv_file.name.split(".")[0]
-
-    assessment = str(csv_filename).split("_")[-1].capitalize()
-    date = str(csv_filename).split("_")[0]
-    try:
-        date = datetime.strptime(date, "%y%m%d")
-    except ValueError:
-        date = None
-
-    tribe = str(tribe_dir).split("/")[-1]
-
-    template = Path(config["templates"]) / "tpl_evaluation.ipynb"
-
-    dest = Path(config["output"]) / tribe / csv_filename
-    dest.mkdir(parents=True, exist_ok=True)
-
-    click.echo(f"Building {assessment} ({date:%d/%m/%y}) report")
-    pm.execute_notebook(
-        str(template),
-        str(dest / f"{assessment}.ipynb"),
-        parameters=dict(
-            tribe=tribe, assessment=assessment, date=f"{date:%d/%m/%y}", csv_file=str(csv_file.absolute())
-        ),
-    )
-
-    # with open(csv_file.parent / "description.yml") as f:
-    #     tribe_desc = yaml.load(f, Loader=yaml.FullLoader)
-
-    # template = Path(config["templates"]) / "tpl_student.ipynb"
-    # dest = Path(config["output"]) / tribe / csv_filename / "students"
-    # dest.mkdir(parents=True, exist_ok=True)
-
-    # for st in tribe_desc["students"]:
-    #     click.echo(f"Building {st} report on {assessment}")
-    #     pm.execute_notebook(
-    #         str(template),
-    #         str(dest / f"{st}.ipynb"),
-    #         parameters=dict(tribe=tribe, student=st, source=str(tribe_dir.absolute())),
-    #     )
+@click.option("--debug", default=0, help="Debug mode for dash")
+def dashboard(debug):
+    dash.run_server(debug=bool(debug))
 
+if __name__ == "__main__":
+    cli()

requirements.txt

@@ -1,69 +1,4 @@
-ansiwrap==0.8.4
-attrs==19.1.0
-backcall==0.1.0
-bleach==3.1.0
-certifi==2019.6.16
-chardet==3.0.4
-Click==7.0
-colorama==0.4.1
-cycler==0.10.0
-decorator==4.4.0
-defusedxml==0.6.0
-entrypoints==0.3
-future==0.17.1
-idna==2.8
-importlib-resources==1.0.2
-ipykernel==5.1.1
-ipython==7.7.0
-ipython-genutils==0.2.0
-ipywidgets==7.5.1
-jedi==0.14.1
-Jinja2==2.10.1
-jsonschema==3.0.2
-jupyter==1.0.0
-jupyter-client==5.3.1
-jupyter-console==6.0.0
-jupyter-core==4.5.0
-jupytex==0.0.3
-kiwisolver==1.1.0
-MarkupSafe==1.1.1
-matplotlib==3.1.1
-mistune==0.8.4
-nbconvert==5.5.0
-nbformat==4.4.0
-notebook==6.0.0
-numpy==1.17.0
-pandas==0.25.0
-pandocfilters==1.4.2
-papermill==1.0.1
-parso==0.5.1
-pexpect==4.7.0
-pickleshare==0.7.5
-prometheus-client==0.7.1
-prompt-toolkit==2.0.9
-ptyprocess==0.6.0
-Pygments==2.4.2
-pyparsing==2.4.2
-pyrsistent==0.15.4
-python-dateutil==2.8.0
-pytz==2019.2
-PyYAML==5.1.2
-pyzmq==18.0.2
-qtconsole==4.5.2
--e git+git_opytex:/lafrite/recopytex.git@e9a8310f151ead60434ae944d726a2fd22b23d06#egg=Recopytex
-requests==2.22.0
-scipy==1.3.0
-seaborn==0.9.0
-Send2Trash==1.5.0
-six==1.12.0
-tenacity==5.0.4
-terminado==0.8.2
-testpath==0.4.2
-textwrap3==0.9.2
-tornado==6.0.3
-tqdm==4.32.2
-traitlets==4.3.2
-urllib3==1.25.3
-wcwidth==0.1.7
-webencodings==0.5.1
-widgetsnbextension==3.5.1
+pandas
+click
+papermill
+prompt_toolkit

requirements_dev.txt

@@ -0,0 +1,69 @@
+ansiwrap
+attrs
+backcall
+bleach
+certifi
+chardet
+Click
+colorama
+cycler
+decorator
+defusedxml
+entrypoints
+future
+idna
+importlib-resources
+ipykernel
+ipython
+ipython-genutils
+ipywidgets
+jedi
+Jinja2
+jsonschema
+jupyter
+jupyter-client
+jupyter-console
+jupyter-core
+jupytex
+kiwisolver
+MarkupSafe
+matplotlib
+mistune
+nbconvert
+nbformat
+notebook
+numpy
+pandas
+pandocfilters
+papermill
+parso
+pexpect
+pickleshare
+prometheus-client
+prompt-toolkit
+ptyprocess
+Pygments
+pyparsing
+pyrsistent
+python-dateutil
+pytz
+PyYAML
+pyzmq
+qtconsole
+-e git+git_opytex:/lafrite/recopytex.git@e9a8310f151ead60434ae944d726a2fd22b23d06#egg=Recopytex
+requests
+scipy
+seaborn
+Send2Trash
+six
+tenacity
+terminado
+testpath
+textwrap3
+tornado
+tqdm
+traitlets
+urllib3
+wcwidth
+webencodings
+widgetsnbextension

test_config.yml

@@ -0,0 +1,13 @@
+---
+source: ./example
+output: ./output
+templates: templates/
+
+tribes:
+    Tribe1:
+        name: Tribe1
+        type: Type1
+        students: tribe1.csv
+    Tribe2:
+        name: Tribe2
+        students: tribe2.csv