From 32578b4f779fc4301c4a96ec086ec31ea6adede1 Mon Sep 17 00:00:00 2001
From: mcoth <mcoth@dtu.dk>
Date: Sun, 17 Nov 2024 16:43:27 +0100
Subject: [PATCH] Upload New File
---
Import_data.py | 44 ++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 44 insertions(+)
create mode 100644 Import_data.py
diff --git a/Import_data.py b/Import_data.py
new file mode 100644
index 0000000..58c600b
--- /dev/null
+++ b/Import_data.py
@@ -0,0 +1,44 @@
+"""
+Created on Sun Sep 1 12:13:23 2024
+
+@author: Maya Coulson Theodorsen (mcoth@dtu.dk)
+
+This script imports the CSV data file, drops participants who have not consented
+to their data being used for research, filters incomplete datasets, keeps only
+one dataset for each participant
+
+"""
+
+#Import all necessary packages
+import pandas as pd
+
+# Define import of data
+def load_data(file_path):
+ # Import data
+ data_original = pd.read_csv("data6_9_2023.csv", encoding='latin-1', sep = ';')
+ data = data_original
+ print('Total amount of participants/measurements:', data.shape[0])
+
+ # Delete the data of individuals who do not consent to research
+ data = data.drop(data.index[data['Forskning'] == False])
+
+ #Check the counts to make sure all who haven't consented are deleted
+ data['Forskning'].value_counts()
+
+ #Display amout that have given consent
+ print('Total amount of participants wtih consent:', data.shape[0])
+
+ # Delete incomplete datasets, drop duplicates
+ data = data[data['PCL_t0'].notna()]
+ data = data[data['DASS_D_t0'].notna()]
+ data = data[data['DASS_S_t0'].notna()]
+ data = data[data['DASS_A_t0'].notna()]
+ data = data[data['q0003_0001'].notna()]
+ data = data.drop_duplicates(subset='lbnr')
+
+ print('Total amount of unique participants wtih complete data:', data.shape[0])
+
+ data_complete = data.copy()
+ data_complete = data_complete.reset_index()
+
+ return data_complete
\ No newline at end of file
--
GitLab