ProjectPro omairaasim

## project_1_step_1_load_data.py
# Step 1 Load Data
import pandas as pd
dataset = pd.read_csv('Salary_Data.csv')
X = dataset.iloc[:, :-1].values
y = dataset.iloc[:,1].values

## project_1_step_2_split_dataset.py
# Step 2: Split data into training and testing
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=1/3, random_state=0)

## project_1_step_3_fit_model.py
# Step 3: Fit Simple Linear Regression to Training Data
from sklearn.linear_model import LinearRegression
regressor = LinearRegression()
regressor.fit(X_train, y_train)

## project_1_step_4_predict.py
# Step 4: Make Prediction
y_pred = regressor.predict(X_test)

## project_1_step_5_visualize_training.py
# Step 5 - Visualize training set results
import matplotlib.pyplot as plt
# plot the actual data points of training set
plt.scatter(X_train, y_train, color = 'red')
# plot the regression line
plt.plot(X_train, regressor.predict(X_train), color='blue')
plt.title('Salary vs Experience (Training set)')
plt.xlabel('Years of Experience')
plt.ylabel('Salary')
plt.show()

## project_1_step_6_visualize_test.py
# Step 6 - Visualize test set results
import matplotlib.pyplot as plt
# plot the actual data points of test set
plt.scatter(X_test, y_test, color = 'red')
# plot the regression line (same as above)
plt.plot(X_train, regressor.predict(X_train), color='blue')
plt.title('Salary vs Experience (Test set)')
plt.xlabel('Years of Experience')
plt.ylabel('Salary')
plt.show()

## project_1_step_7_new_prediction.py
# Step 7 - Make new prediction
new_salary_pred = regressor.predict([[15]])

## project_1.py
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Sun Sep  1 19:14:35 2019

@author: omairaasim
"""

# Step 1 Load Data
import pandas as pd

## project_2_step_1_load_data.py
# Step 1 - Load Data
import pandas as pd
dataset = pd.read_csv("50_Startups.csv")
X = dataset.iloc[:,:-1].values
y = dataset.iloc[:,4].values

## project_2_step_2_convert_text.py
# Step 2 - Encode Categorical Data
from sklearn.preprocessing import OneHotEncoder
from sklearn.compose import ColumnTransformer
import numpy as np
ct = ColumnTransformer(transformers=[('encoder',OneHotEncoder(),[3])], remainder='passthrough')
X = np.array(ct.fit_transform(X))
	# Step 1 Load Data
	import pandas as pd
	dataset = pd.read_csv('Salary_Data.csv')
	X = dataset.iloc[:, :-1].values
	y = dataset.iloc[:,1].values
	# Step 2: Split data into training and testing
	from sklearn.model_selection import train_test_split
	X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=1/3, random_state=0)
	# Step 3: Fit Simple Linear Regression to Training Data
	from sklearn.linear_model import LinearRegression
	regressor = LinearRegression()
	regressor.fit(X_train, y_train)
	# Step 5 - Visualize training set results
	import matplotlib.pyplot as plt
	# plot the actual data points of training set
	plt.scatter(X_train, y_train, color = 'red')
	# plot the regression line
	plt.plot(X_train, regressor.predict(X_train), color='blue')
	plt.title('Salary vs Experience (Training set)')
	plt.xlabel('Years of Experience')
	plt.ylabel('Salary')
	plt.show()
	# Step 6 - Visualize test set results
	import matplotlib.pyplot as plt
	# plot the actual data points of test set
	plt.scatter(X_test, y_test, color = 'red')
	# plot the regression line (same as above)
	plt.plot(X_train, regressor.predict(X_train), color='blue')
	plt.title('Salary vs Experience (Test set)')
	plt.xlabel('Years of Experience')
	plt.ylabel('Salary')
	plt.show()
	# Step 7 - Make new prediction
	new_salary_pred = regressor.predict([[15]])
	#!/usr/bin/env python3
	# -- coding: utf-8 --
	"""
	Created on Sun Sep 1 19:14:35 2019

	@author: omairaasim
	"""

	# Step 1 Load Data
	import pandas as pd
	# Step 1 - Load Data
	import pandas as pd
	dataset = pd.read_csv("50_Startups.csv")
	X = dataset.iloc[:,:-1].values
	y = dataset.iloc[:,4].values
	# Step 2 - Encode Categorical Data
	from sklearn.preprocessing import OneHotEncoder
	from sklearn.compose import ColumnTransformer
	import numpy as np
	ct = ColumnTransformer(transformers=[('encoder',OneHotEncoder(),[3])], remainder='passthrough')
	X = np.array(ct.fit_transform(X))