From 97b24f92deb4fec4eb161edd7dcf68bd090be113 Mon Sep 17 00:00:00 2001 From: Heiko J Schick Date: Sat, 20 Nov 2021 21:00:07 +0100 Subject: [PATCH] Added function to load data --- data_visualisation.py | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) create mode 100644 data_visualisation.py diff --git a/data_visualisation.py b/data_visualisation.py new file mode 100644 index 0000000..709afe2 --- /dev/null +++ b/data_visualisation.py @@ -0,0 +1,22 @@ +import pandas as pd +import numpy as np + +filename = "48yrs/cores.dat" +df = pd.read_csv(filename, header = None, sep = "\s+") +df.columns = ["year", "cores"] +df = df.dropna() +df['year'] = df.year.astype(float) + +cores_missing = df['cores'].isna() +print(df.loc[cores_missing,:]) + +print(df['year'].isna().sum()) +print(df['cores'].isna().sum()) + +print(df) +print("-------------") +print(df.dtypes) +print("-------------") +print(df.shape) +print("-------------") +print(df.info())