From 69ceebd98a5621ffc8fd5604febdb10154c9f040 Mon Sep 17 00:00:00 2001
From: zhang yongquan <zhyqestudy@163.com>
Date: Mon, 6 Aug 2018 14:05:00 +0800
Subject: [PATCH] add Day 1.py

---
 Code/Day 1_Data Prepocessing.py | 68 +++++++++++++++++++++++++++++++++
 1 file changed, 68 insertions(+)
 create mode 100644 Code/Day 1_Data Prepocessing.py

diff --git a/Code/Day 1_Data Prepocessing.py b/Code/Day 1_Data Prepocessing.py
new file mode 100644
index 0000000..435d940
--- /dev/null
+++ b/Code/Day 1_Data Prepocessing.py	
@@ -0,0 +1,68 @@
+#Day 1: Data Prepocessing
+
+#Step 1: Importing the libraries
+import numpy as np
+import pandas as pd
+
+#Step 2: Importing dataset
+dataset = pd.read_csv('Data.csv')
+X = dataset.iloc[ : , :-1].values
+Y = dataset.iloc[ : , 3].values
+print("Step 2: Importing dataset")
+print("X")
+print(X)
+print("Y")
+print(Y)
+
+#Step 3: Handling the missing data
+from sklearn.preprocessing import Imputer
+imputer = Imputer(missing_values = "NaN", strategy = "mean", axis = 0)
+imputer = imputer.fit(X[ : , 1:3])
+X[ : , 1:3] = imputer.transform(X[ : , 1:3])
+print("---------------------")
+print("Step 3: Handling the missing data")
+print("step2")
+print("X")
+print(X)
+
+#Step 4: Encoding categorical data
+from sklearn.preprocessing import LabelEncoder, OneHotEncoder
+labelencoder_X = LabelEncoder()
+X[ : , 0] = labelencoder_X.fit_transform(X[ : , 0])
+#Creating a dummy variable
+onehotencoder = OneHotEncoder(categorical_features = [0])
+X = onehotencoder.fit_transform(X).toarray()
+labelencoder_Y = LabelEncoder()
+Y =  labelencoder_Y.fit_transform(Y)
+print("---------------------")
+print("Step 4: Encoding categorical data")
+print("X")
+print(X)
+print("Y")
+print(Y)
+
+#Step 5: Splitting the datasets into training sets and Test sets
+from sklearn.cross_validation import train_test_split
+X_train, X_test, Y_train, Y_test = train_test_split( X , Y , test_size = 0.2, random_state = 0)
+print("---------------------")
+print("Step 5: Splitting the datasets into training sets and Test sets")
+print("X_train")
+print(X_train)
+print("X_test")
+print(X_test)
+print("Y_train")
+print(Y_train)
+print("Y_test")
+print(Y_test)
+
+#Step 6: Feature Scaling
+from sklearn.preprocessing import StandardScaler
+sc_X = StandardScaler()
+X_train = sc_X.fit_transform(X_train)
+X_test = sc_X.fit_transform(X_test)
+print("---------------------")
+print("Step 6: Feature Scaling")
+print("X_train")
+print(X_train)
+print("X_test")
+print(X_test)
\ No newline at end of file