Minor changes

data_visualisation.py

@@ -1,22 +1,26 @@
 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)
+def print_data(df):
+    # print("=========================================")
+    print(df)
+    # print("-----------------------------------------")
+    # print(df.dtypes)
+    # print("-----------------------------------------")
+    # print(df.shape)
+    # print("-----------------------------------------")
+    # print(df.info())
 
-cores_missing = df['cores'].isna()
-print(df.loc[cores_missing,:])
+def load_data(filename, columns):
+    df = pd.read_csv(filename, header = None, sep = "\s+", comment ='#')
+    df.columns = columns
+    df = df.dropna()
+    df[columns[0]] = df.year.astype(float)
+    print_data(df)
+    return df
 
-print(df['year'].isna().sum())
-print(df['cores'].isna().sum())
-
-print(df)
-print("-------------")
-print(df.dtypes)
-print("-------------")
-print(df.shape)
-print("-------------")
-print(df.info())
+df_cores       = load_data("48yrs/cores.dat",       ["year", "cores"])
+df_frequency   = load_data("48yrs/frequency.dat",   ["year", "frequency"])
+df_specint     = load_data("48yrs/specint.dat",     ["year", "specint"])
+df_transistors = load_data("48yrs/transistors.dat", ["year", "transistors"])
+df_watts       = load_data("48yrs/watts.dat",       ["year", "watts"])