def createScatterPlot(name,x,y):
"""Creates scatter plot
Args:
name(str): name of value being plotted against MPG
x(list): list of values used for the x-axis
y(list): list of values used for the y-axis
Notes:
Used in AutoData.ipynb
"""
#Calculate slope
m, b = utils.compute_slope_intercept(x,y)
#Use matplotlib to create histogram
plt.figure()
plt.scatter(x,y)
plt.plot([min(x), max(x)], [m*min(x)+b, m*max(x)+b], c="r",lw=5)
#Create title
plt.title("{} vs. MPG Scatter Plot".format(name))
plt.xlabel(name)
plt.ylabel("MPG")
#Annotate
#Calculate correlation coefficient
corrCoeff = utils.calculateCorrCoeff(x,y)
plt.annotate("$corCoef = {}$".format(str(corrCoeff)),xy=(.85,.9),xycoords="axes fraction", horizontalalignment="center",color="blue")
#Calculate covariance
covariance = utils.calculateCovariance(x,y)
plt.annotate("$cov = {}$".format(str(covariance)),xy=(.85,.8),xycoords="axes fraction", horizontalalignment="center",color="blue")
#Show Diagram
plt.show()
def movieScatterPlot(x_title,x,y_title,y):
"""Creates scatter plot for movies data.
Args:
x_title(str): name of values on x-axis
x(list): list of x-axis values
y_title(str): name of values on y-axis
y(list): list of y-axis values
Notes:
Used in Movies.ipynb
"""
#Remove percentages
x = utils.removePercentage(x)
y = utils.removePercentage(y)
#Calculate slope
m, b = utils.compute_slope_intercept(x,y)
#Use matplotlib to create histogram
plt.figure() #figsize=(10,10))
plt.scatter(x,y)
plt.plot([min(x), max(x)], [m*min(x)+b, m*max(x)+b], c="r",lw=5)
#Create labels
plt.title("{} vs. {} Scatter Plot".format(x_title,y_title))
plt.xlabel("{} Ratings".format(x_title))
plt.ylabel("{} Ratings".format(y_title))
#Show Diagram
plt.show()
def fit(self, X_train, y_train):
"""Fits a simple linear regression line to X_train and y_train.
Args:
X_train(list of list of numeric vals): The list of training samples
The shape of X_train is (n_train_samples, n_features)
Note that n_features for simple regression is 1, so each sample is a list
with one element e.g. [[0], [1], [2]]
y_train(list of numeric vals): The target y values (parallel to X_train)
The shape of y_train is n_train_samples
"""
x = myutils.convert_2D_to_1D(X_train)
y = myutils.convert_2D_to_1D(y_train)
slope, intercept = myutils.compute_slope_intercept(x, y_train)
self.slope = slope
self.intercept = intercept
def fit(self, X_train, y_train):
"""Fits a simple linear regression line to X_train and y_train.
Args:
X_train(list of list of numeric vals): The list of training samples
The shape of X_train is (n_train_samples, n_features)
Note that n_features for simple regression is 1, so each sample is a list
with one element e.g. [[0], [1], [2]]
y_train(list of numeric vals): The target y values (parallel to X_train)
The shape of y_train is n_train_samples
"""
x_train_1d = []
for sample in X_train:
x_train_1d.append(sample[0])
m, b = myutils.compute_slope_intercept(x_train_1d, y_train)
self.slope = m
self.intercept = b