Feat: csv extraction and flattening
This commit is contained in:
parent
9358c10b47
commit
2296615cb4
@ -0,0 +1,15 @@
|
|||||||
|
#!/usr/bin/env python
|
||||||
|
# encoding: utf-8
|
||||||
|
|
||||||
|
NO_STUDENT_COLUMNS = [
|
||||||
|
"Trimestre",
|
||||||
|
"Nom",
|
||||||
|
"Date",
|
||||||
|
"Exercice",
|
||||||
|
"Question",
|
||||||
|
"Competence",
|
||||||
|
"Domaine",
|
||||||
|
"Commentaire",
|
||||||
|
"Bareme",
|
||||||
|
"Niveau",
|
||||||
|
]
|
||||||
75
recopytex/csv_extraction.py
Normal file
75
recopytex/csv_extraction.py
Normal file
@ -0,0 +1,75 @@
|
|||||||
|
#!/usr/bin/env python
|
||||||
|
# encoding: utf-8
|
||||||
|
|
||||||
|
""" Extracting data from xlsx files """
|
||||||
|
|
||||||
|
import pandas as pd
|
||||||
|
from . import NO_STUDENT_COLUMNS
|
||||||
|
|
||||||
|
pd.set_option("Precision", 2)
|
||||||
|
|
||||||
|
|
||||||
|
def extract_students(df, no_student_columns=NO_STUDENT_COLUMNS):
|
||||||
|
""" 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_STUDENT_COLUMNS):
|
||||||
|
""" Flat the ws for students
|
||||||
|
|
||||||
|
: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_STUDENT_COLUMNS
|
||||||
|
- 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="student",
|
||||||
|
value_name="score",
|
||||||
|
)
|
||||||
|
)
|
||||||
|
return pd.concat(scores)
|
||||||
|
|
||||||
|
|
||||||
|
def flat_clear_csv(csv_df, no_student_columns=NO_STUDENT_COLUMNS):
|
||||||
|
""" Flat and clear the dataframe extracted from csv
|
||||||
|
|
||||||
|
:param csv_df: data frame read from csv
|
||||||
|
:param no_student_columns: columns that are not students
|
||||||
|
:return: dataframe with one row per questions and students
|
||||||
|
|
||||||
|
"""
|
||||||
|
df = flat_df_students(csv_df)
|
||||||
|
|
||||||
|
df.columns = df.columns.map(lambda x: x.lower())
|
||||||
|
|
||||||
|
df["question"].fillna("", inplace=True)
|
||||||
|
df["exercice"].fillna("", inplace=True)
|
||||||
|
df["commentaire"].fillna("", inplace=True)
|
||||||
|
df["competence"].fillna("", inplace=True)
|
||||||
|
|
||||||
|
return df
|
||||||
|
|
||||||
|
|
||||||
|
# -----------------------------
|
||||||
|
# Reglages pour 'vim'
|
||||||
|
# vim:set autoindent expandtab tabstop=4 shiftwidth=4:
|
||||||
|
# cursor: 16 del
|
||||||
@ -2,7 +2,7 @@
|
|||||||
"cells": [
|
"cells": [
|
||||||
{
|
{
|
||||||
"cell_type": "code",
|
"cell_type": "code",
|
||||||
"execution_count": 4,
|
"execution_count": 1,
|
||||||
"metadata": {},
|
"metadata": {},
|
||||||
"outputs": [],
|
"outputs": [],
|
||||||
"source": [
|
"source": [
|
||||||
@ -10,12 +10,13 @@
|
|||||||
"from IPython.display import DisplayHandle\n",
|
"from IPython.display import DisplayHandle\n",
|
||||||
"import pandas as pd\n",
|
"import pandas as pd\n",
|
||||||
"from pathlib import Path\n",
|
"from pathlib import Path\n",
|
||||||
"from datetime import datetime"
|
"from datetime import datetime\n",
|
||||||
|
"from recopytex.csv_extraction import flat_clear_csv"
|
||||||
]
|
]
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"cell_type": "code",
|
"cell_type": "code",
|
||||||
"execution_count": 8,
|
"execution_count": 2,
|
||||||
"metadata": {
|
"metadata": {
|
||||||
"tags": [
|
"tags": [
|
||||||
"parameters"
|
"parameters"
|
||||||
@ -24,35 +25,20 @@
|
|||||||
"outputs": [],
|
"outputs": [],
|
||||||
"source": [
|
"source": [
|
||||||
"tribe = \"308\"\n",
|
"tribe = \"308\"\n",
|
||||||
"assessment = \"161114_dm2\"\n",
|
"assessment = \"DM1\"\n",
|
||||||
"csv_file = Path(f\"./sheets/{tribe}/{assessment}.csv\")"
|
"date = \"15/09/16\"\n",
|
||||||
|
"csv_file = Path(f\"../sheets/{tribe}/160915_{assessment}.csv\")"
|
||||||
]
|
]
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"cell_type": "code",
|
"cell_type": "code",
|
||||||
"execution_count": 9,
|
"execution_count": 3,
|
||||||
"metadata": {},
|
|
||||||
"outputs": [],
|
|
||||||
"source": [
|
|
||||||
"split_ass = assessment.split(\"_\")\n",
|
|
||||||
"if len(split_ass) > 1:\n",
|
|
||||||
" date, *assessment = assessment.split(\"_\")\n",
|
|
||||||
" date = datetime.strptime(date, \"%y%m%d\")\n",
|
|
||||||
" assessment = ' '.join(assessment)\n",
|
|
||||||
"else:\n",
|
|
||||||
" date = None\n",
|
|
||||||
" assessment = split_ass[0]"
|
|
||||||
]
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"cell_type": "code",
|
|
||||||
"execution_count": 16,
|
|
||||||
"metadata": {},
|
"metadata": {},
|
||||||
"outputs": [
|
"outputs": [
|
||||||
{
|
{
|
||||||
"data": {
|
"data": {
|
||||||
"text/markdown": [
|
"text/markdown": [
|
||||||
"# dm2 (14/11/2016) pour 308"
|
"# DM1 (15/09/16) pour 308"
|
||||||
],
|
],
|
||||||
"text/plain": [
|
"text/plain": [
|
||||||
"<IPython.core.display.Markdown object>"
|
"<IPython.core.display.Markdown object>"
|
||||||
@ -66,7 +52,154 @@
|
|||||||
"if date is None:\n",
|
"if date is None:\n",
|
||||||
" display(md(f\"# {assessment} pour {tribe}\"))\n",
|
" display(md(f\"# {assessment} pour {tribe}\"))\n",
|
||||||
"else:\n",
|
"else:\n",
|
||||||
" display(md(f\"# {assessment} ({date:%d/%m/%Y}) pour {tribe}\"))"
|
" display(md(f\"# {assessment} ({date}) pour {tribe}\"))"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 4,
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"data": {
|
||||||
|
"text/html": [
|
||||||
|
"<div>\n",
|
||||||
|
"<style scoped>\n",
|
||||||
|
" .dataframe tbody tr th:only-of-type {\n",
|
||||||
|
" vertical-align: middle;\n",
|
||||||
|
" }\n",
|
||||||
|
"\n",
|
||||||
|
" .dataframe tbody tr th {\n",
|
||||||
|
" vertical-align: top;\n",
|
||||||
|
" }\n",
|
||||||
|
"\n",
|
||||||
|
" .dataframe thead th {\n",
|
||||||
|
" text-align: right;\n",
|
||||||
|
" }\n",
|
||||||
|
"</style>\n",
|
||||||
|
"<table border=\"1\" class=\"dataframe\">\n",
|
||||||
|
" <thead>\n",
|
||||||
|
" <tr style=\"text-align: right;\">\n",
|
||||||
|
" <th></th>\n",
|
||||||
|
" <th>trimestre</th>\n",
|
||||||
|
" <th>nom</th>\n",
|
||||||
|
" <th>date</th>\n",
|
||||||
|
" <th>exercice</th>\n",
|
||||||
|
" <th>question</th>\n",
|
||||||
|
" <th>competence</th>\n",
|
||||||
|
" <th>domaine</th>\n",
|
||||||
|
" <th>commentaire</th>\n",
|
||||||
|
" <th>bareme</th>\n",
|
||||||
|
" <th>niveau</th>\n",
|
||||||
|
" <th>student</th>\n",
|
||||||
|
" <th>score</th>\n",
|
||||||
|
" </tr>\n",
|
||||||
|
" </thead>\n",
|
||||||
|
" <tbody>\n",
|
||||||
|
" <tr>\n",
|
||||||
|
" <th>0</th>\n",
|
||||||
|
" <td>1</td>\n",
|
||||||
|
" <td>DM1</td>\n",
|
||||||
|
" <td>15/09/16</td>\n",
|
||||||
|
" <td>1</td>\n",
|
||||||
|
" <td>1.1</td>\n",
|
||||||
|
" <td>Cal</td>\n",
|
||||||
|
" <td>Prio</td>\n",
|
||||||
|
" <td></td>\n",
|
||||||
|
" <td>1.0</td>\n",
|
||||||
|
" <td>1</td>\n",
|
||||||
|
" <td>ABDOU Asmahane</td>\n",
|
||||||
|
" <td>2</td>\n",
|
||||||
|
" </tr>\n",
|
||||||
|
" <tr>\n",
|
||||||
|
" <th>1</th>\n",
|
||||||
|
" <td>1</td>\n",
|
||||||
|
" <td>DM1</td>\n",
|
||||||
|
" <td>15/09/16</td>\n",
|
||||||
|
" <td>1</td>\n",
|
||||||
|
" <td>1.2</td>\n",
|
||||||
|
" <td>Cal</td>\n",
|
||||||
|
" <td>Prio</td>\n",
|
||||||
|
" <td></td>\n",
|
||||||
|
" <td>1.0</td>\n",
|
||||||
|
" <td>1</td>\n",
|
||||||
|
" <td>ABDOU Asmahane</td>\n",
|
||||||
|
" <td>3</td>\n",
|
||||||
|
" </tr>\n",
|
||||||
|
" <tr>\n",
|
||||||
|
" <th>2</th>\n",
|
||||||
|
" <td>1</td>\n",
|
||||||
|
" <td>DM1</td>\n",
|
||||||
|
" <td>15/09/16</td>\n",
|
||||||
|
" <td>1</td>\n",
|
||||||
|
" <td>1.3</td>\n",
|
||||||
|
" <td>Cal</td>\n",
|
||||||
|
" <td>Prio</td>\n",
|
||||||
|
" <td></td>\n",
|
||||||
|
" <td>1.0</td>\n",
|
||||||
|
" <td>1</td>\n",
|
||||||
|
" <td>ABDOU Asmahane</td>\n",
|
||||||
|
" <td>2</td>\n",
|
||||||
|
" </tr>\n",
|
||||||
|
" <tr>\n",
|
||||||
|
" <th>3</th>\n",
|
||||||
|
" <td>1</td>\n",
|
||||||
|
" <td>DM1</td>\n",
|
||||||
|
" <td>15/09/16</td>\n",
|
||||||
|
" <td>1</td>\n",
|
||||||
|
" <td>1.4</td>\n",
|
||||||
|
" <td>Cal</td>\n",
|
||||||
|
" <td>Prio</td>\n",
|
||||||
|
" <td></td>\n",
|
||||||
|
" <td>1.0</td>\n",
|
||||||
|
" <td>1</td>\n",
|
||||||
|
" <td>ABDOU Asmahane</td>\n",
|
||||||
|
" <td>2</td>\n",
|
||||||
|
" </tr>\n",
|
||||||
|
" <tr>\n",
|
||||||
|
" <th>4</th>\n",
|
||||||
|
" <td>1</td>\n",
|
||||||
|
" <td>DM1</td>\n",
|
||||||
|
" <td>15/09/16</td>\n",
|
||||||
|
" <td>1</td>\n",
|
||||||
|
" <td>1.5</td>\n",
|
||||||
|
" <td>Cal</td>\n",
|
||||||
|
" <td>Prio</td>\n",
|
||||||
|
" <td></td>\n",
|
||||||
|
" <td>1.0</td>\n",
|
||||||
|
" <td>1</td>\n",
|
||||||
|
" <td>ABDOU Asmahane</td>\n",
|
||||||
|
" <td>2</td>\n",
|
||||||
|
" </tr>\n",
|
||||||
|
" </tbody>\n",
|
||||||
|
"</table>\n",
|
||||||
|
"</div>"
|
||||||
|
],
|
||||||
|
"text/plain": [
|
||||||
|
" trimestre nom date exercice question competence domaine commentaire \\\n",
|
||||||
|
"0 1 DM1 15/09/16 1 1.1 Cal Prio \n",
|
||||||
|
"1 1 DM1 15/09/16 1 1.2 Cal Prio \n",
|
||||||
|
"2 1 DM1 15/09/16 1 1.3 Cal Prio \n",
|
||||||
|
"3 1 DM1 15/09/16 1 1.4 Cal Prio \n",
|
||||||
|
"4 1 DM1 15/09/16 1 1.5 Cal Prio \n",
|
||||||
|
"\n",
|
||||||
|
" bareme niveau student score \n",
|
||||||
|
"0 1.0 1 ABDOU Asmahane 2 \n",
|
||||||
|
"1 1.0 1 ABDOU Asmahane 3 \n",
|
||||||
|
"2 1.0 1 ABDOU Asmahane 2 \n",
|
||||||
|
"3 1.0 1 ABDOU Asmahane 2 \n",
|
||||||
|
"4 1.0 1 ABDOU Asmahane 2 "
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"execution_count": 4,
|
||||||
|
"metadata": {},
|
||||||
|
"output_type": "execute_result"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"source": [
|
||||||
|
"stack_scores = pd.read_csv(csv_file)\n",
|
||||||
|
"scores = flat_clear_csv(stack_scores)\n",
|
||||||
|
"scores.head()"
|
||||||
]
|
]
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
|
|||||||
Loading…
Reference in New Issue
Block a user