def split_data_set(request):
pk = request.data['id']
file = get_object_or_404(File, id=pk)
df = dataframe_from_file(file.file)
response = {'training_set': {}, 'test_set': {}, 'error': False}
try:
training_set, test_set = train_test_split(df, test_size=0.2)
response = {
'training_set': format_to_json(pd.DataFrame(training_set)),
'test_set': format_to_json(pd.DataFrame(test_set)),
'error': False
}
except Exception as e:
response['error'] = str(e)
return Response(response)
def execute_query(request):
pk = request.data['id']
file = get_object_or_404(File, id=pk)
query_string = request.data['query']
df = dataframe_from_file(file.file)
results = sqldf(query_string, locals())
return Response(format_to_json(results))
def filter_by_columns(request):
pk = request.data['id']
file = get_object_or_404(File, id=pk)
columns = request.data['columns_names'].split(',')
columns_list = []
df = dataframe_from_file(file.file)
if columns and columns[0]:
for column in columns:
columns_list.append(column)
df = df[columns_list]
return Response(format_to_json(df))
def transform(request):
pk = request.data['id']
column = request.data['column']
convert_to = request.data['type']
file = get_object_or_404(File, id=pk)
df = dataframe_from_file(file.file)
try:
df = df.astype({column: convert_to}, errors='ignore')
except Exception as e:
pass
return Response(format_to_json(df))
def search_value(request):
pk = request.data['id']
file = get_object_or_404(File, id=pk)
df = dataframe_from_file(file.file)
value = request.data['value']
data = ''
if value in df.columns:
data = df[[value]]
elif value in df.index:
data = df.loc[[value]]
else:
data = df[df.isin([value]).any(1)]
return Response(format_to_json(data))
def filter_by_columns_and_rows(request):
pk = request.data['id']
file = get_object_or_404(File, id=pk)
df = dataframe_from_file(file.file)
begin_line = int(
request.data['beginLine']) if request.data['beginLine'] else ''
end_line = int(request.data['endLine']) if request.data['endLine'] else ''
begin_column = int(
request.data['beginColumn']) if request.data['beginColumn'] else ''
end_column = int(
request.data['endColumn']) if request.data['endColumn'] else ''
last_line = df.shape[0] + 1
last_column = df.shape[1] + 1
filtered_data = df
if (begin_line != '' and
(begin_line < 0 or begin_line >= last_line - 1)) or (
end_line != '' and end_line > last_line) or (
begin_column != '' and
(begin_column < 0 or begin_column >= last_column - 1)) or (
end_column != '' and end_column > last_column):
return HttpResponse(
"Indices invalides (Index lignes ou colonnes en dehors de la plage autorisée)"
)
if begin_line != '' and end_line != '' and begin_column != '' and end_column != '':
filtered_data = df.iloc[begin_line:end_line, begin_column:end_column]
elif begin_line == '' and end_line != '' and begin_column != '' and end_column != '':
filtered_data = df.iloc[:end_line, begin_column:end_column]
elif begin_line == '' and end_line == '' and begin_column != '' and end_column != '':
filtered_data = df.iloc[:, begin_column:end_column]
elif begin_line == '' and end_line == '' and begin_column == '' and end_column != '':
filtered_data = df.iloc[:, :end_column]
elif begin_line != '' and end_line == '' and begin_column == '' and end_column == '':
filtered_data = df.iloc[begin_line:, :]
elif begin_line != '' and end_line != '' and begin_column == '' and end_column == '':
filtered_data = df.iloc[begin_line:end_line, :]
elif begin_line != '' and end_line != '' and begin_column != '' and end_column == '':
filtered_data = df.iloc[begin_line:end_line, begin_column:]
elif begin_line != '' and end_line == '' and begin_column == '' and end_column != '':
filtered_data = df.iloc[begin_line:, :end_column]
elif begin_line != '' and end_line != '' and begin_column == '' and end_column != '':
filtered_data = df.iloc[begin_line:end_line, :end_column]
elif begin_line != '' and end_line == '' and begin_column != '' and end_column != '':
filtered_data = df.iloc[begin_line:, begin_column:end_column]
elif begin_line == '' and end_line != '' and begin_column != '' and end_column == '':
filtered_data = df.iloc[:end_line, begin_column:]
elif begin_line != '' and end_line == '' and begin_column != '' and end_column == '':
filtered_data = df.iloc[begin_line:, begin_column:]
elif begin_line == '' and end_line != '' and begin_column == '' and end_column != '':
filtered_data = df.iloc[:end_line, :end_column]
return HttpResponse(format_to_json(filtered_data))
def upload(request):
file = File(file=request.data['file'])
name, ext = os.path.splitext(file.file.name)
file.title = name
file.save()
df = dataframe_from_file(file.file)
json_response = {'data': 'Extension non valide'}
if len(df) != 0:
json_data = format_to_json(df)
columns = df.columns.values.tolist()
json_response = {
'name': name,
'data': json_data,
'path': file.file.url,
'columnsNames': columns,
'id': file.id,
'size': df.size,
'rows': df.shape[0],
'columns': df.shape[1],
}
else:
file.delete()
return Response(json_response)
def reset(request):
pk = request.data['id']
file = get_object_or_404(File, id=pk)
df = dataframe_from_file(file.file)
return Response(format_to_json(df))
def describe(request):
pk = request.data['id']
file = get_object_or_404(File, id=pk)
df = dataframe_from_file(file.file)
json_object = format_to_json(df.describe().transpose())
return Response(json_object)