def preprocessing_pdf():
file_name = request.args.get("filename")
#preprocess = UserData.get_preprocess_from_id(id)
preprocess = UserData.get_user_preprocess(g.user["id"], file_name)
col_sel_method_set = ['Average', 'Max', 'Min', 'Interquartile range']
if (preprocess['col_sel_method'] == ''):
preprocess_data = {
"file_name": preprocess['file_name'],
"annotation_table": '-',
"prob_mthd": '-',
"normalize": preprocess['scaling'],
"imputation": preprocess['imputation'],
"volcano_hash": preprocess['volcano_hash'],
"fold": preprocess['fold'],
"pvalue": preprocess['pvalue'],
"univariate_length": preprocess['length'],
"fr_univariate_hash": preprocess['fr_univariate_hash']
}
else:
preprocess_data = {
"file_name":
preprocess['file_name'],
"annotation_table":
(preprocess['annotation_table']).replace('/AnnotationTbls/', ''),
"prob_mthd":
col_sel_method_set[int(preprocess['col_sel_method']) - 1],
"normalize":
preprocess['scaling'],
"imputation":
preprocess['imputation'],
"volcano_hash":
preprocess['volcano_hash'],
"fold":
preprocess['fold'],
"pvalue":
preprocess['pvalue'],
"univariate_length":
preprocess['length'],
"fr_univariate_hash":
preprocess['fr_univariate_hash']
}
preprocess_data_plot = {
"volcano_hash": preprocess['volcano_hash'],
"fold": preprocess['fold'],
"pvalue": preprocess['pvalue'],
"univariate_length": preprocess['length'],
"fr_univariate_hash": preprocess['fr_univariate_hash']
}
return render_template("pdf/preprocess_pdf.html",
data=preprocess_data,
data_after_norm=preprocess['after_norm_set'],
data_plot=preprocess_data_plot,
clf_results=preprocess['classification_result_set'])
def skip_df_mapping():
user_id = g.user['id']
file_name = request.args.get("selected_file")
if not file_name:
return redirect('./pre')
file_path = USER_PATH / str(user_id) / file_name
UserData.delete_preprocess_file(user_id, file_name)
UserData.add_preprocess(user_id, file_name, file_path.as_posix(), '', '',
'')
pre_process_id = UserData.get_user_preprocess(user_id, file_name)['id']
df = PreProcess.getDF(file_path)
data = PreProcess.get_df_details(df, None)
session[file_name] = data
return redirect(
url_for('preprocess.scaling_imputation') + "?id=" +
str(pre_process_id))
def view_merge_df():
user_id = g.user["id"]
annotation_table = request.form.get("anno_tbl")
col_sel_method = request.form.get("column_selection")
file_name = request.form.get("available_files")
if annotation_table and col_sel_method and file_name:
file_path = USER_PATH / str(user_id) / file_name
# Delete query if file already pre-processed
UserData.delete_preprocess_file(user_id, file_name)
if annotation_table == 'other':
file = request.files['chooseFile']
if file and allowed_file(file.filename):
annotation_table = secure_filename(file.filename)
path_csv = ANNOTATION_TBL / "other" / (str(user_id) + "_" +
annotation_table)
# Delete same file uploaded
result = UserData.get_user_file_by_file_name(
user_id, annotation_table)
annotation_df = pd.read_csv(file, usecols=[0, 1], header=0)
col = annotation_df.columns
if "ID" in col and "Gene Symbol" in col and len(col) == 2:
annotation_df.to_csv(path_csv, index=False)
else:
flash(
"Wrong Format: Gene Symbol and/or ID column not found in annotation table."
)
return redirect('/pre')
else:
return abort(403)
df = PreProcess.mergeDF(file_path, path_csv)
if result is None:
view_path = "/AnnotationTbls/other/" + str(
user_id) + "_" + annotation_table
UserData.add_file(annotation_table,
annotation_table.split('.')[1], view_path,
user_id, 1, 0)
else:
# load df
annotation_table_path = UPLOAD_FOLDER.as_posix() + annotation_table
df = PreProcess.mergeDF(file_path, Path(annotation_table_path))
if df is None:
flash("Couldn't merge dataset with annotation table")
return redirect('/pre')
y = PreProcess.getDF(file_path)
if 'class' not in y.columns:
flash("Wrong Format: class column not found.")
return redirect('/pre')
y = y['class']
data = PreProcess.get_df_details(df, y)
session[file_name] = data
df = df.dropna(axis=0, subset=['Gene Symbol'])
df = PreProcess.probe2Symbol(df, int(col_sel_method))
merge_name = "merge_" + file_name
merge_path = USER_PATH / str(user_id) / "tmp" / merge_name
merge_path_str = merge_path.as_posix()
PreProcess.saveDF(df, merge_path_str)
# save data to the Database
UserData.add_preprocess(user_id, file_name, file_path.as_posix(),
annotation_table, col_sel_method,
merge_path_str)
pre_process_id = UserData.get_user_preprocess(user_id, file_name)['id']
if len(df.columns) > 100:
df_view = df.iloc[:, 0:100].head(15)
else:
df_view = df.head(15)
return render_template("preprocess/step-2.html",
tables=[df_view.to_html(classes='data')],
details=data,
pre_process_id=pre_process_id,
file_name=merge_name)
return redirect('/pre')
