Second server backup

Author: SoumitraAgarwal

Server backup 2/Scripts/custom.py

@@ -0,0 +1,37 @@
+# Simple Linear Regression
+# Importing the libraries
+import numpy as np
+import pandas as pd
+import pickle
+
+# Importing the dataset
+dataset = pd.read_csv('/home/soumitra/Working/Salary_Data.csv')
+X = dataset.iloc[:, :-1].values
+y = dataset.iloc[:, 1].values
+
+# Splitting the dataset into the Training set and Test set
+from sklearn.cross_validation import train_test_split
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size =0.33,random_state = 0)
+
+# Feature Scaling
+"""from sklearn.preprocessing import StandardScaler
+sc_X = StandardScaler()
+X_train = sc_X.fit_transform(X_train)
+X_test = sc_X.transform(X_test)
+sc_y = StandardScaler()
+y_train = sc_y.fit_transform(y_train)"""
+
+# Fitting Simple Linear Regression to the Training set
+from sklearn.linear_model import LinearRegression
+regressor = LinearRegression()
+regressor.fit(X_train, y_train)
+
+# Predicting the Test set results
+y_pred = regressor.predict(X_test)
+coef_ = regressor.coef_
+intercept_ = regressor.intercept_ 
+
+# Score of prediction model
+from sklearn.metrics import r2_score
+score = r2_score(y_test, y_pred)
+pickle.dump([y_pred, score, coef_, intercept_], open("/home/soumitra/attributes.p", "wb"), protocol = 2)

Server backup 2/Scripts/decision_tree_classification.py

@@ -0,0 +1,28 @@
+# Decision Tree Classification
+
+# Importing the libraries
+import numpy as np
+import matplotlib.pyplot as plt
+import pandas as pd
+import pickle 
+
+# Importing the dataset
+dataset = open(workdata, 'r')
+mat 	= dataset.readlines()
+time = []
+for row in mat:
+	pres = row.split()
+	pres = [float(ro) for ro in pres]
+	time.append(pres)
+
+time = np.array(time)
+
+X_train = time[:, :-1]
+y_train = time[:, -1]
+
+# Fitting Decision Tree Classification to the Training set
+from sklearn.tree import DecisionTreeClassifier
+classifier = DecisionTreeClassifier(parameters)
+classifier.fit(X_train, y_train)
+
+pickle.dump(classifier,open(hoemdir + "/attributes.p", "wb"), protocol = 2 )

Server backup 2/Scripts/decision_tree_regression.py

@@ -0,0 +1,42 @@
+# Regression Template
+
+# Importing the libraries
+import numpy as np
+import matplotlib.pyplot as plt
+import pandas as pd
+import pickle
+
+# Importing the dataset
+# Importing the dataset
+dataset = open(workdata, 'r')
+mat 	= dataset.readlines()
+time = []
+for row in mat:
+	pres = row.split()
+	pres = [float(ro) for ro in pres]
+	time.append(pres)
+
+time = np.array(time)
+
+X = time[:, :-1]
+y = time[:, -1]
+
+# Splitting the dataset into the Training set and Test set
+"""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)"""
+
+# Feature Scaling
+"""
+from sklearn.preprocessing import StandardScaler
+sc_X = StandardScaler()
+X= sc_X.fit_transform(X)
+sc_y = StandardScaler()
+y = sc_y.fit_transform(y)"""
+
+# Fitting the Regression Model to the dataset
+# Create your regressor here
+from sklearn.tree import DecisionTreeRegressor
+regressor = DecisionTreeRegressor(parameters)
+regressor.fit(X, y)
+
+pickle.dump(regressor,open(hoemdir + "/attributes.p", "wb"), protocol = 2 )

Server backup 2/Scripts/heirarchial_clustering.py

@@ -0,0 +1,25 @@
+# Hierarchical Clustering
+
+# Importing the libraries
+import numpy as np
+import pandas as pd
+import pickle
+
+# Importing the dataset
+dataset = open('/home/soumitra/Working/data', 'r')
+mat 	= dataset.readlines()
+time = []
+for row in mat:
+	pres = row.split()
+	pres = [float(ro) for ro in pres]
+	time.append(pres)
+
+time = np.array(time)
+X = time
+
+# Fitting Hierarchical Clustering to the dataset
+from sklearn.cluster import AgglomerativeClustering
+hc = AgglomerativeClustering(parameters)
+y_hc = hc.fit_predict(X)
+
+pickle.dump(y_hc ,open("/home/soumitra/attributes.p", "wb"), protocol = 2 )

Server backup 2/Scripts/kmeans_clustering.py

@@ -0,0 +1,29 @@
+# K-Means Clustering
+
+# Importing the libraries
+import numpy as np
+import matplotlib.pyplot as plt
+import pandas as pd
+import pickle
+
+# Importing the dataset
+dataset = open(workdata, 'r')
+mat 	= dataset.readlines()
+time = []
+for row in mat:
+	pres = row.split()
+	pres = [float(ro) for ro in pres]
+	time.append(pres)
+
+time = np.array(time)
+X = time
+
+# Using the elbow method to find the optimal number of clusters
+from sklearn.cluster import KMeans
+kmeans = KMeans(parameters)
+kmeans.fit(X)
+    
+
+ 
+# Export the results to pickle file
+pickle.dump(kmeans,open(homedir + "/attributes.p", "wb"), protocol = 2 )

Server backup 2/Scripts/knn_classification.py

@@ -0,0 +1,28 @@
+# K-Nearest Neighbors (K-NN)
+# Classification template
+
+# Importing the libraries
+import numpy as np
+import pickle
+import pandas as pd
+
+# Importing the dataset
+dataset = open(workdata, 'r')
+mat 	= dataset.readlines()
+time = []
+for row in mat:
+	pres = row.split()
+	pres = [float(ro) for ro in pres]
+	time.append(pres)
+
+time = np.array(time)
+X = time[:, :-1]
+y = time[:, -1]
+
+# Fitting classifier to the Training set
+from sklearn.neighbors import KNeighborsClassifier 
+classifier = KNeighborsClassifier(parameters)
+classifier.fit(X, y)
+
+# Export results to pickle file
+pickle.dump(classifier,open(homedir + "/attributes.p", "wb"), protocol = 2 )

Server backup 2/Scripts/linear_regression.py

@@ -0,0 +1,24 @@
+# Simple Linear Regression
+# Importing the libraries
+import numpy as np
+import pickle
+
+# Importing the dataset
+dataset = open(workdata, 'r')
+mat 	= dataset.readlines()
+time = []
+for row in mat:
+	pres = row.split()
+	pres = [float(ro) for ro in pres]
+	time.append(pres)
+
+time = np.array(time)
+X = time[:, :-1]
+y = time[:, -1]
+
+# Fitting Simple Linear Regression to the Training set
+from sklearn.linear_model import LinearRegression
+regressor = LinearRegression()
+regressor.fit(X, y)
+
+pickle.dump(regressor, open(homedir + "/attributes.p", "wb"), protocol = 2)

Server backup 2/Scripts/logistic.py

@@ -0,0 +1,26 @@
+
+# Importing the libraries
+import numpy as np
+import pickle
+
+# Importing the dataset
+# Importing the dataset
+dataset = open('/home/soumitra/Working/data', 'r')
+mat 	= dataset.readlines()
+time = []
+for row in mat:
+	pres = row.split()
+	pres = [float(ro) for ro in pres]
+	time.append(pres)
+
+time = np.array(time)
+
+X = time[:, :-1]
+y = time[:, -1]
+
+#Fitting dataset to logistic regression
+from sklearn.linear_model import LogisticRegression
+classifier = LogisticRegression()
+classifier.fit(X, y)
+
+pickle.dump(classifier,open("/home/soumitra/attributes.p", "wb"), protocol = 2 )    

Server backup 2/Scripts/logistic_regression.py

@@ -0,0 +1,26 @@
+
+# Importing the libraries
+import numpy as np
+import pickle
+
+# Importing the dataset
+# Importing the dataset
+dataset = open(workdata, 'r')
+mat 	= dataset.readlines()
+time = []
+for row in mat:
+	pres = row.split()
+	pres = [float(ro) for ro in pres]
+	time.append(pres)
+
+time = np.array(time)
+
+X = time[:, :-1]
+y = time[:, -1]
+
+#Fitting dataset to logistic regression
+from sklearn.linear_model import LogisticRegression
+classifier = LogisticRegression(parameters)
+classifier.fit(X, y)
+
+pickle.dump(classifier,open(homedir + "/attributes.p", "wb"), protocol = 2 )    

Server backup 2/Scripts/multiple_linear_regression.py

@@ -0,0 +1,37 @@
+# -*- coding: utf-8 -*-
+"""
+Created on Mon July 8 23:31:52 2017
+
+@author: Mandar
+"""
+
+# Data Preprocessing Template
+
+# Importing the libraries
+import numpy as np
+import matplotlib.pyplot as plt
+import pandas as pd
+import pickle
+
+# Importing the dataset
+dataset = open(workdata, 'r')
+mat 	= dataset.readlines()
+time = []
+for row in mat:
+	pres = row.split()
+	pres = [float(ro) for ro in pres]
+	time.append(pres)
+
+time = np.array(time)
+
+X = time[:, :-1]
+y = time[:, -1]
+
+
+#Fitting mutilpls linear regreesion to training set
+from sklearn.linear_model import LinearRegression
+regressor = LinearRegression(parameters)
+regressor.fit(X, y)
+
+
+pickle.dump(regressor ,open(homedir + "attributes.p", "wb"), protocol = 2 )

Server backup 2/Scripts/naive_bayes_GaussianNB.py

@@ -0,0 +1,28 @@
+# Naive Bayes
+
+# Importing the libraries
+import numpy as np
+import pandas as pd
+import pickle
+
+# Importing the dataset
+dataset = open(workdata, 'r')
+mat 	= dataset.readlines()
+time = []
+for row in mat:
+	pres = row.split()
+	pres = [float(ro) for ro in pres]
+	time.append(pres)
+
+time = np.array(time)
+
+X = time[:, :-1]
+y = time[:, -1]
+
+# Fitting Naive Bayes to the Training set
+from sklearn.naive_bayes import GaussianNB
+classifier = GaussianNB(parameters)
+classifier.fit(X, y)
+
+
+pickle.dump(classifier,open(homedir + "/attributes.p", "wb"), protocol = 2 )    

Server backup 2/Scripts/naive_bayes_MultinomialNB.py

@@ -0,0 +1,28 @@
+# Naive Bayes
+
+# Importing the libraries
+import numpy as np
+import pandas as pd
+import pickle
+
+# Importing the dataset
+dataset = open(workdata, 'r')
+mat 	= dataset.readlines()
+time = []
+for row in mat:
+	pres = row.split()
+	pres = [float(ro) for ro in pres]
+	time.append(pres)
+
+time = np.array(time)
+
+X = time[:, :-1]
+y = time[:, -1]
+
+# Fitting Naive Bayes to the Training set
+from sklearn.naive_bayes import GaussianNB
+classifier = GaussianNB(parameters)
+classifier.fit(X, y)
+
+pickle.dump(classifier ,open("/home/soumitra/attributes.p", "wb"), protocol = 2 )    
+