main.py

@@ -4,4 +4,9 @@ sys.path.append('./src/back/')
 
 import load_csv as l 
 
-l.csv_value()
+df = l.return_csv("./data.csv")
+l.csv_value(df)
+
+l.csv_value(df)
+
+l.csv_stadadisation_Z(df,"Vehicle Year")

src/back/load_csv.py

@@ -1,20 +1,35 @@
 import pandas as pd
+import numpy  as np
 
+def return_csv(path):
+    df = pd.read_csv(path)
+    return df
 
-def csv_value():
-    df = pd.read_csv('./data.csv')
-    # print(df.head())
-
+def csv_value(df):
     #print all detail 
-    # df.info()
-
+    df.info()
     # Print number of missing value for each column
-    # print(df.isna().sum())
-
+    print(df.isna().sum())
     # Useless values
-    # Off-Road Description         -> 156170
-    # Municipality                 -> 152979
-    # Related Non-Motorist         -> 166642
-    # Non-Motorist Substance Abuse -> 167788
-    # Circumstance                 -> 140746
+
+
+def csv_check(df):
+    for col in df:
+        print("-"*12)
+        print(col)
+        print("-"*12)
+        print(df[col].unique())
+
+
+def csv_norm_min_max(df,col):
+    maValue = df[col].max
+    miValue = df[col].min
+    df[col] = (df[col] - df[col].min()) / (df[col].max() - df[col].min())
     return df
+
+def csv_stadadisation_Z(df,col):
+    mean_col1 = df[col].mean()
+    std_col1 = df[col].std()
+    df[col] = (df[col] - mean_col1) / std_col1
+    return df[col]
+