Refactor local_weighted_learning.py to use np.array#8069

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
cclauss merged 4 commits into from
Jan 2, 2023
+68 −51
Merged

Refactor local_weighted_learning.py to use np.array#8069

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
f7ba9da
updating DIRECTORY.md
Jan 2, 2023
ac662b3
Format local_weighted_learning.py doctests for clarity
tianyizheng02 Jan 2, 2023
dae74a7
Refactor local_weighted_learning.py to use np.array instead of np.mat
tianyizheng02 Jan 2, 2023
8a1f929
Update local_weighted_learning.py documentation
tianyizheng02 Jan 2, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 2 additions & 1 deletion DIRECTORY.md
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -123,6 +123,7 @@
* [Huffman](compression/huffman.py)
* [Lempel Ziv](compression/lempel_ziv.py)
* [Lempel Ziv Decompress](compression/lempel_ziv_decompress.py)
* [Lz77](compression/lz77.py)
* [Peak Signal To Noise Ratio](compression/peak_signal_to_noise_ratio.py)
* [Run Length Encoding](compression/run_length_encoding.py)

Expand DownExpand Up@@ -1162,7 +1163,7 @@
* [Get Amazon Product Data](web_programming/get_amazon_product_data.py)
* [Get Imdb Top 250 Movies Csv](web_programming/get_imdb_top_250_movies_csv.py)
* [Get Imdbtop](web_programming/get_imdbtop.py)
* [Get Top Billioners](web_programming/get_top_billioners.py)
* [Get Top Billionaires](web_programming/get_top_billionaires.py)
* [Get Top Hn Posts](web_programming/get_top_hn_posts.py)
* [Get User Tweets](web_programming/get_user_tweets.py)
* [Giphy](web_programming/giphy.py)
Expand Down
116 changes: 66 additions & 50 deletions machine_learning/local_weighted_learning/local_weighted_learning.py
View file
Open in desktop
Original file line numberDiff line numberDiff line change
@@ -1,116 +1,128 @@
# Required imports to run this file
import matplotlib.pyplot as plt
import numpy as np


# weighted matrix
def weighted_matrix(point: np.mat, training_data_x: np.mat, bandwidth: float) -> np.mat:
def weighted_matrix(
point: np.array, training_data_x: np.array, bandwidth: float
) -> np.array:
"""
Calculate the weight for every point in the
data set. It takes training_point , query_point, and tau
Here Tau is not a fixed value it can be varied depends on output.
tau --> bandwidth
xmat -->Training data
point --> the x where we want to make predictions
>>> weighted_matrix(np.array([1., 1.]),np.mat([[16.99, 10.34], [21.01,23.68],
... [24.59,25.69]]), 0.6)
matrix([[1.43807972e-207, 0.00000000e+000, 0.00000000e+000],
[0.00000000e+000, 0.00000000e+000, 0.00000000e+000],
[0.00000000e+000, 0.00000000e+000, 0.00000000e+000]])
Calculate the weight for every point in the data set.
point --> the x value at which we want to make predictions
>>> weighted_matrix(
... np.array([1., 1.]),
... np.array([[16.99, 10.34], [21.01,23.68], [24.59,25.69]]),
... 0.6
... )
array([[1.43807972e-207, 0.00000000e+000, 0.00000000e+000],
[0.00000000e+000, 0.00000000e+000, 0.00000000e+000],
[0.00000000e+000, 0.00000000e+000, 0.00000000e+000]])
"""
# m is the number of training samples
m, n = np.shape(training_data_x)
# Initializing weights as identity matrix
weights = np.mat(np.eye(m))
m, _ = np.shape(training_data_x) # m is the number of training samples
weights = np.eye(m) # Initializing weights as identity matrix

# calculating weights for all training examples [x(i)'s]
for j in range(m):
diff = point - training_data_x[j]
weights[j, j] = np.exp(diff * diff.T / (-2.0 * bandwidth**2))
weights[j, j] = np.exp(diff @ diff.T / (-2.0 * bandwidth**2))
return weights


def local_weight(
point: np.mat, training_data_x: np.mat, training_data_y: np.mat, bandwidth: float
) -> np.mat:
point: np.array,
training_data_x: np.array,
training_data_y: np.array,
bandwidth: float,
) -> np.array:
"""
Calculate the local weights using the weight_matrix function on training data.
Return the weighted matrix.
>>> local_weight(np.array([1., 1.]),np.mat([[16.99, 10.34], [21.01,23.68],
... [24.59,25.69]]),np.mat([[1.01, 1.66, 3.5]]), 0.6)
matrix([[0.00873174],
[0.08272556]])
>>> local_weight(
... np.array([1., 1.]),
... np.array([[16.99, 10.34], [21.01,23.68], [24.59,25.69]]),
... np.array([[1.01, 1.66, 3.5]]),
... 0.6
... )
array([[0.00873174],
[0.08272556]])
"""
weight = weighted_matrix(point, training_data_x, bandwidth)
w = (training_data_x.T * (weight * training_data_x)).I * (
training_data_x.T * weight * training_data_y.T
w = np.linalg.inv(training_data_x.T @ (weight @ training_data_x)) @ (
training_data_x.T @ weight @ training_data_y.T
)

return w


def local_weight_regression(
training_data_x: np.mat, training_data_y: np.mat, bandwidth: float
) -> np.mat:
training_data_x: np.array, training_data_y: np.array, bandwidth: float
) -> np.array:
"""
Calculate predictions for each data point on axis.
>>> local_weight_regression(np.mat([[16.99, 10.34], [21.01,23.68],
... [24.59,25.69]]),np.mat([[1.01, 1.66, 3.5]]), 0.6)
Calculate predictions for each data point on axis
>>> local_weight_regression(
... np.array([[16.99, 10.34], [21.01, 23.68], [24.59, 25.69]]),
... np.array([[1.01, 1.66, 3.5]]),
... 0.6
... )
array([1.07173261, 1.65970737, 3.50160179])
"""
m, n = np.shape(training_data_x)
m, _ = np.shape(training_data_x)
ypred = np.zeros(m)

for i, item in enumerate(training_data_x):
ypred[i] = item * local_weight(
ypred[i] = item @ local_weight(
item, training_data_x, training_data_y, bandwidth
)

return ypred


def load_data(dataset_name: str, cola_name: str, colb_name: str) -> np.mat:
def load_data(
dataset_name: str, cola_name: str, colb_name: str
) -> tuple[np.array, np.array, np.array, np.array]:
"""
Function used for loading data from the seaborn splitting into x and y points
Load data from seaborn and split it into x and y points
"""
import seaborn as sns

data = sns.load_dataset(dataset_name)
col_a = np.array(data[cola_name]) # total_bill
col_b = np.array(data[colb_name]) # tip

mcol_a = np.mat(col_a)
mcol_b = np.mat(col_b)
mcol_a = col_a.copy()
mcol_b = col_b.copy()

m = np.shape(mcol_b)[1]
one = np.ones((1, m), dtype=int)
one = np.ones(np.shape(mcol_b)[0], dtype=int)

# horizontal stacking
training_data_x = np.hstack((one.T, mcol_a.T))
# pairing elements of one and mcol_a
training_data_x = np.column_stack((one, mcol_a))

return training_data_x, mcol_b, col_a, col_b


def get_preds(training_data_x: np.mat, mcol_b: np.mat, tau: float) -> np.ndarray:
def get_preds(training_data_x: np.array, mcol_b: np.array, tau: float) -> np.array:
"""
Get predictions with minimum error for each training data
>>> get_preds(np.mat([[16.99, 10.34], [21.01,23.68],
... [24.59,25.69]]),np.mat([[1.01, 1.66, 3.5]]), 0.6)
>>> get_preds(
... np.array([[16.99, 10.34], [21.01, 23.68], [24.59, 25.69]]),
... np.array([[1.01, 1.66, 3.5]]),
... 0.6
... )
array([1.07173261, 1.65970737, 3.50160179])
"""
ypred = local_weight_regression(training_data_x, mcol_b, tau)
return ypred


def plot_preds(
training_data_x: np.mat,
predictions: np.ndarray,
col_x: np.ndarray,
col_y: np.ndarray,
training_data_x: np.array,
predictions: np.array,
col_x: np.array,
col_y: np.array,
cola_name: str,
colb_name: str,
) -> plt.plot:
"""
This function used to plot predictions and display the graph
Plot predictions and display the graph
"""
xsort = training_data_x.copy()
xsort.sort(axis=0)
Expand All@@ -128,6 +140,10 @@ def plot_preds(


if __name__ == "__main__":
import doctest

doctest.testmod()

training_data_x, mcol_b, col_a, col_b = load_data("tips", "total_bill", "tip")
predictions = get_preds(training_data_x, mcol_b, 0.5)
plot_preds(training_data_x, predictions, col_a, col_b, "total_bill", "tip")
, 'i'); if (__m === '*' || __re.test(location.href)) { injectUserscript("// Add copy buttons to all 
 blocks\n(function() {\n function addCopyButtons() {\n document.querySelectorAll('pre code').forEach(function(codeBlock) {\n if (codeBlock.parentElement.hasAttribute('data-copy-added')) return;\n codeBlock.parentElement.setAttribute('data-copy-added', 'true');\n \n var btn = document.createElement('button');\n btn.textContent = 'Copy';\n btn.style.cssText = 'position:absolute;top:4px;right:4px;padding:2px 8px;font-size:11px;background:#4ecdc4;border:none;border-radius:4px;color:#1a1a2e;cursor:pointer;opacity:0.7;transition:opacity 0.2s;';\n btn.onmouseover = function() { this.style.opacity = '1'; };\n btn.onmouseout = function() { this.style.opacity = '0.7'; };\n btn.onclick = function() {\n navigator.clipboard.writeText(codeBlock.textContent).then(function() {\n btn.textContent = 'Copied!';\n setTimeout(function() { btn.textContent = 'Copy'; }, 1500);\n });\n };\n codeBlock.parentElement.style.position = 'relative';\n codeBlock.parentElement.appendChild(btn);\n });\n }\n \n addCopyButtons();\n \n // Re-run on dynamic content\n var observer = new MutationObserver(addCopyButtons);\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "Add Copy Buttons to Code Blocks");
}
} catch(__e) { console.warn('[Userscript:Add Copy Buttons to Code Blocks]', __e); }
})();
(function(){
try {
var __m = "github.com";
var __re = new RegExp('^' + "github\\.com" + '

Skip to content
Refactor local_weighted_learning.py to use np.array#8069

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

cclauss
merged 4 commits into

from

Jan 2, 2023

+68

−51

 Merged


Refactor local_weighted_learning.py to use np.array#8069
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


4 commits


Select commit
Hold shift + click to select a range
f7ba9da

updating DIRECTORY.md

Jan 2, 2023
ac662b3

Format local_weighted_learning.py doctests for clarity


tianyizheng02 Jan 2, 2023
dae74a7

Refactor local_weighted_learning.py to use np.array instead of np.mat


tianyizheng02 Jan 2, 2023
8a1f929

Update local_weighted_learning.py documentation


tianyizheng02 Jan 2, 2023

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


3 changes: 2 additions & 1 deletion
DIRECTORY.md

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -123,6 +123,7 @@
 * [Huffman](compression/huffman.py)
 * [Lempel Ziv](compression/lempel_ziv.py)
 * [Lempel Ziv Decompress](compression/lempel_ziv_decompress.py)
 * [Lz77](compression/lz77.py)
 * [Peak Signal To Noise Ratio](compression/peak_signal_to_noise_ratio.py)
 * [Run Length Encoding](compression/run_length_encoding.py)

Expand DownExpand Up@@ -1162,7 +1163,7 @@
 * [Get Amazon Product Data](web_programming/get_amazon_product_data.py)
 * [Get Imdb Top 250 Movies Csv](web_programming/get_imdb_top_250_movies_csv.py)
 * [Get Imdbtop](web_programming/get_imdbtop.py)
 * [Get Top Billioners](web_programming/get_top_billioners.py)
 * [Get Top Billionaires](web_programming/get_top_billionaires.py)
 * [Get Top Hn Posts](web_programming/get_top_hn_posts.py)
 * [Get User Tweets](web_programming/get_user_tweets.py)
 * [Giphy](web_programming/giphy.py)
Expand Down

116 changes: 66 additions & 50 deletions
machine_learning/local_weighted_learning/local_weighted_learning.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -1,116 +1,128 @@
# Required imports to run this file
import matplotlib.pyplot as plt
import numpy as np


# weighted matrix
def weighted_matrix(point: np.mat, training_data_x: np.mat, bandwidth: float) -> np.mat:
def weighted_matrix(
 point: np.array, training_data_x: np.array, bandwidth: float
) -> np.array:
 """
 Calculate the weight for every point in the
 data set. It takes training_point , query_point, and tau
 Here Tau is not a fixed value it can be varied depends on output.
 tau --> bandwidth
 xmat -->Training data
 point --> the x where we want to make predictions
 >>> weighted_matrix(np.array([1., 1.]),np.mat([[16.99, 10.34], [21.01,23.68],
 ... [24.59,25.69]]), 0.6)
 matrix([[1.43807972e-207, 0.00000000e+000, 0.00000000e+000],
 [0.00000000e+000, 0.00000000e+000, 0.00000000e+000],
 [0.00000000e+000, 0.00000000e+000, 0.00000000e+000]])
 Calculate the weight for every point in the data set.
 point --> the x value at which we want to make predictions
 >>> weighted_matrix(
 ... np.array([1., 1.]),
 ... np.array([[16.99, 10.34], [21.01,23.68], [24.59,25.69]]),
 ... 0.6
 ... )
 array([[1.43807972e-207, 0.00000000e+000, 0.00000000e+000],
 [0.00000000e+000, 0.00000000e+000, 0.00000000e+000],
 [0.00000000e+000, 0.00000000e+000, 0.00000000e+000]])
 """
 # m is the number of training samples
 m, n = np.shape(training_data_x)
 # Initializing weights as identity matrix
 weights = np.mat(np.eye(m))
 m, _ = np.shape(training_data_x) # m is the number of training samples
 weights = np.eye(m) # Initializing weights as identity matrix

 # calculating weights for all training examples [x(i)'s]
 for j in range(m):
 diff = point - training_data_x[j]
 weights[j, j] = np.exp(diff * diff.T / (-2.0 * bandwidth**2))
 weights[j, j] = np.exp(diff @ diff.T / (-2.0 * bandwidth**2))
 return weights


def local_weight(
 point: np.mat, training_data_x: np.mat, training_data_y: np.mat, bandwidth: float
) -> np.mat:
 point: np.array,
 training_data_x: np.array,
 training_data_y: np.array,
 bandwidth: float,
) -> np.array:
 """
 Calculate the local weights using the weight_matrix function on training data.
 Return the weighted matrix.
 >>> local_weight(np.array([1., 1.]),np.mat([[16.99, 10.34], [21.01,23.68],
 ... [24.59,25.69]]),np.mat([[1.01, 1.66, 3.5]]), 0.6)
 matrix([[0.00873174],
 [0.08272556]])
 >>> local_weight(
 ... np.array([1., 1.]),
 ... np.array([[16.99, 10.34], [21.01,23.68], [24.59,25.69]]),
 ... np.array([[1.01, 1.66, 3.5]]),
 ... 0.6
 ... )
 array([[0.00873174],
 [0.08272556]])
 """
 weight = weighted_matrix(point, training_data_x, bandwidth)
 w = (training_data_x.T * (weight * training_data_x)).I * (
 training_data_x.T * weight * training_data_y.T
 w = np.linalg.inv(training_data_x.T @ (weight @ training_data_x)) @ (
 training_data_x.T @ weight @ training_data_y.T
 )

 return w


def local_weight_regression(
 training_data_x: np.mat, training_data_y: np.mat, bandwidth: float
) -> np.mat:
 training_data_x: np.array, training_data_y: np.array, bandwidth: float
) -> np.array:
 """
 Calculate predictions for each data point on axis.
 >>> local_weight_regression(np.mat([[16.99, 10.34], [21.01,23.68],
 ... [24.59,25.69]]),np.mat([[1.01, 1.66, 3.5]]), 0.6)
 Calculate predictions for each data point on axis
 >>> local_weight_regression(
 ... np.array([[16.99, 10.34], [21.01, 23.68], [24.59, 25.69]]),
 ... np.array([[1.01, 1.66, 3.5]]),
 ... 0.6
 ... )
 array([1.07173261, 1.65970737, 3.50160179])
 """
 m, n = np.shape(training_data_x)
 m, _ = np.shape(training_data_x)
 ypred = np.zeros(m)

 for i, item in enumerate(training_data_x):
 ypred[i] = item * local_weight(
 ypred[i] = item @ local_weight(
 item, training_data_x, training_data_y, bandwidth
 )

 return ypred


def load_data(dataset_name: str, cola_name: str, colb_name: str) -> np.mat:
def load_data(
 dataset_name: str, cola_name: str, colb_name: str
) -> tuple[np.array, np.array, np.array, np.array]:
 """
Function used for loading data from the seaborn splitting into x and y points
Load data from seaborn and split it into x and y points
 """
 import seaborn as sns

 data = sns.load_dataset(dataset_name)
 col_a = np.array(data[cola_name]) # total_bill
 col_b = np.array(data[colb_name]) # tip

 mcol_a = np.mat(col_a)
 mcol_b = np.mat(col_b)
 mcol_a = col_a.copy()
 mcol_b = col_b.copy()

 m = np.shape(mcol_b)[1]
 one = np.ones((1, m), dtype=int)
 one = np.ones(np.shape(mcol_b)[0], dtype=int)

 # horizontal stacking
 training_data_x = np.hstack((one.T, mcol_a.T))
 # pairing elements of one and mcol_a
 training_data_x = np.column_stack((one, mcol_a))

 return training_data_x, mcol_b, col_a, col_b


def get_preds(training_data_x: np.mat, mcol_b: np.mat, tau: float) -> np.ndarray:
def get_preds(training_data_x: np.array, mcol_b: np.array, tau: float) -> np.array:
 """
 Get predictions with minimum error for each training data
 >>> get_preds(np.mat([[16.99, 10.34], [21.01,23.68],
 ... [24.59,25.69]]),np.mat([[1.01, 1.66, 3.5]]), 0.6)
 >>> get_preds(
 ... np.array([[16.99, 10.34], [21.01, 23.68], [24.59, 25.69]]),
 ... np.array([[1.01, 1.66, 3.5]]),
 ... 0.6
 ... )
 array([1.07173261, 1.65970737, 3.50160179])
 """
 ypred = local_weight_regression(training_data_x, mcol_b, tau)
 return ypred


def plot_preds(
 training_data_x: np.mat,
 predictions: np.ndarray,
 col_x: np.ndarray,
 col_y: np.ndarray,
 training_data_x: np.array,
 predictions: np.array,
 col_x: np.array,
 col_y: np.array,
 cola_name: str,
 colb_name: str,
) -> plt.plot:
 """
This function used to plot predictions and display the graph
Plot predictions and display the graph
 """
 xsort = training_data_x.copy()
 xsort.sort(axis=0)
Expand All@@ -128,6 +140,10 @@ def plot_preds(


if __name__ == "__main__":
 import doctest

 doctest.testmod()

 training_data_x, mcol_b, col_a, col_b = load_data("tips", "total_bill", "tip")
 predictions = get_preds(training_data_x, mcol_b, 0.5)
 plot_preds(training_data_x, predictions, col_a, col_b, "total_bill", "tip")

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Force GitHub README to respect dark mode\n(function() {\n var style = document.createElement('style');\n style.textContent = '\n .markdown-body {\n color-scheme: dark light;\n }\n .markdown-body pre { background: #161b22 !important; }\n .markdown-body code { background: rgba(110, 118, 129, 0.4) !important; }\n .markdown-body table th, .markdown-body table td { border-color: #30363d !important; }\n .markdown-body img { background: #0d1117; }\n .markdown-body blockquote { border-left-color: #8b949e; }\n .markdown-body hr { border-color: #30363d; }\n ';\n document.head.appendChild(style);\n})();", "GitHub Dark Mode README Fix");
}
} catch(__e) { console.warn('[Userscript:GitHub Dark Mode README Fix]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
Refactor local_weighted_learning.py to use np.array#8069

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

cclauss
merged 4 commits into

from

Jan 2, 2023

+68

−51

 Merged


Refactor local_weighted_learning.py to use np.array#8069
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


4 commits


Select commit
Hold shift + click to select a range
f7ba9da

updating DIRECTORY.md

Jan 2, 2023
ac662b3

Format local_weighted_learning.py doctests for clarity


tianyizheng02 Jan 2, 2023
dae74a7

Refactor local_weighted_learning.py to use np.array instead of np.mat


tianyizheng02 Jan 2, 2023
8a1f929

Update local_weighted_learning.py documentation


tianyizheng02 Jan 2, 2023

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


3 changes: 2 additions & 1 deletion
DIRECTORY.md

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -123,6 +123,7 @@
 * [Huffman](compression/huffman.py)
 * [Lempel Ziv](compression/lempel_ziv.py)
 * [Lempel Ziv Decompress](compression/lempel_ziv_decompress.py)
 * [Lz77](compression/lz77.py)
 * [Peak Signal To Noise Ratio](compression/peak_signal_to_noise_ratio.py)
 * [Run Length Encoding](compression/run_length_encoding.py)

Expand DownExpand Up@@ -1162,7 +1163,7 @@
 * [Get Amazon Product Data](web_programming/get_amazon_product_data.py)
 * [Get Imdb Top 250 Movies Csv](web_programming/get_imdb_top_250_movies_csv.py)
 * [Get Imdbtop](web_programming/get_imdbtop.py)
 * [Get Top Billioners](web_programming/get_top_billioners.py)
 * [Get Top Billionaires](web_programming/get_top_billionaires.py)
 * [Get Top Hn Posts](web_programming/get_top_hn_posts.py)
 * [Get User Tweets](web_programming/get_user_tweets.py)
 * [Giphy](web_programming/giphy.py)
Expand Down

116 changes: 66 additions & 50 deletions
machine_learning/local_weighted_learning/local_weighted_learning.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -1,116 +1,128 @@
# Required imports to run this file
import matplotlib.pyplot as plt
import numpy as np


# weighted matrix
def weighted_matrix(point: np.mat, training_data_x: np.mat, bandwidth: float) -> np.mat:
def weighted_matrix(
 point: np.array, training_data_x: np.array, bandwidth: float
) -> np.array:
 """
 Calculate the weight for every point in the
 data set. It takes training_point , query_point, and tau
 Here Tau is not a fixed value it can be varied depends on output.
 tau --> bandwidth
 xmat -->Training data
 point --> the x where we want to make predictions
 >>> weighted_matrix(np.array([1., 1.]),np.mat([[16.99, 10.34], [21.01,23.68],
 ... [24.59,25.69]]), 0.6)
 matrix([[1.43807972e-207, 0.00000000e+000, 0.00000000e+000],
 [0.00000000e+000, 0.00000000e+000, 0.00000000e+000],
 [0.00000000e+000, 0.00000000e+000, 0.00000000e+000]])
 Calculate the weight for every point in the data set.
 point --> the x value at which we want to make predictions
 >>> weighted_matrix(
 ... np.array([1., 1.]),
 ... np.array([[16.99, 10.34], [21.01,23.68], [24.59,25.69]]),
 ... 0.6
 ... )
 array([[1.43807972e-207, 0.00000000e+000, 0.00000000e+000],
 [0.00000000e+000, 0.00000000e+000, 0.00000000e+000],
 [0.00000000e+000, 0.00000000e+000, 0.00000000e+000]])
 """
 # m is the number of training samples
 m, n = np.shape(training_data_x)
 # Initializing weights as identity matrix
 weights = np.mat(np.eye(m))
 m, _ = np.shape(training_data_x) # m is the number of training samples
 weights = np.eye(m) # Initializing weights as identity matrix

 # calculating weights for all training examples [x(i)'s]
 for j in range(m):
 diff = point - training_data_x[j]
 weights[j, j] = np.exp(diff * diff.T / (-2.0 * bandwidth**2))
 weights[j, j] = np.exp(diff @ diff.T / (-2.0 * bandwidth**2))
 return weights


def local_weight(
 point: np.mat, training_data_x: np.mat, training_data_y: np.mat, bandwidth: float
) -> np.mat:
 point: np.array,
 training_data_x: np.array,
 training_data_y: np.array,
 bandwidth: float,
) -> np.array:
 """
 Calculate the local weights using the weight_matrix function on training data.
 Return the weighted matrix.
 >>> local_weight(np.array([1., 1.]),np.mat([[16.99, 10.34], [21.01,23.68],
 ... [24.59,25.69]]),np.mat([[1.01, 1.66, 3.5]]), 0.6)
 matrix([[0.00873174],
 [0.08272556]])
 >>> local_weight(
 ... np.array([1., 1.]),
 ... np.array([[16.99, 10.34], [21.01,23.68], [24.59,25.69]]),
 ... np.array([[1.01, 1.66, 3.5]]),
 ... 0.6
 ... )
 array([[0.00873174],
 [0.08272556]])
 """
 weight = weighted_matrix(point, training_data_x, bandwidth)
 w = (training_data_x.T * (weight * training_data_x)).I * (
 training_data_x.T * weight * training_data_y.T
 w = np.linalg.inv(training_data_x.T @ (weight @ training_data_x)) @ (
 training_data_x.T @ weight @ training_data_y.T
 )

 return w


def local_weight_regression(
 training_data_x: np.mat, training_data_y: np.mat, bandwidth: float
) -> np.mat:
 training_data_x: np.array, training_data_y: np.array, bandwidth: float
) -> np.array:
 """
 Calculate predictions for each data point on axis.
 >>> local_weight_regression(np.mat([[16.99, 10.34], [21.01,23.68],
 ... [24.59,25.69]]),np.mat([[1.01, 1.66, 3.5]]), 0.6)
 Calculate predictions for each data point on axis
 >>> local_weight_regression(
 ... np.array([[16.99, 10.34], [21.01, 23.68], [24.59, 25.69]]),
 ... np.array([[1.01, 1.66, 3.5]]),
 ... 0.6
 ... )
 array([1.07173261, 1.65970737, 3.50160179])
 """
 m, n = np.shape(training_data_x)
 m, _ = np.shape(training_data_x)
 ypred = np.zeros(m)

 for i, item in enumerate(training_data_x):
 ypred[i] = item * local_weight(
 ypred[i] = item @ local_weight(
 item, training_data_x, training_data_y, bandwidth
 )

 return ypred


def load_data(dataset_name: str, cola_name: str, colb_name: str) -> np.mat:
def load_data(
 dataset_name: str, cola_name: str, colb_name: str
) -> tuple[np.array, np.array, np.array, np.array]:
 """
Function used for loading data from the seaborn splitting into x and y points
Load data from seaborn and split it into x and y points
 """
 import seaborn as sns

 data = sns.load_dataset(dataset_name)
 col_a = np.array(data[cola_name]) # total_bill
 col_b = np.array(data[colb_name]) # tip

 mcol_a = np.mat(col_a)
 mcol_b = np.mat(col_b)
 mcol_a = col_a.copy()
 mcol_b = col_b.copy()

 m = np.shape(mcol_b)[1]
 one = np.ones((1, m), dtype=int)
 one = np.ones(np.shape(mcol_b)[0], dtype=int)

 # horizontal stacking
 training_data_x = np.hstack((one.T, mcol_a.T))
 # pairing elements of one and mcol_a
 training_data_x = np.column_stack((one, mcol_a))

 return training_data_x, mcol_b, col_a, col_b


def get_preds(training_data_x: np.mat, mcol_b: np.mat, tau: float) -> np.ndarray:
def get_preds(training_data_x: np.array, mcol_b: np.array, tau: float) -> np.array:
 """
 Get predictions with minimum error for each training data
 >>> get_preds(np.mat([[16.99, 10.34], [21.01,23.68],
 ... [24.59,25.69]]),np.mat([[1.01, 1.66, 3.5]]), 0.6)
 >>> get_preds(
 ... np.array([[16.99, 10.34], [21.01, 23.68], [24.59, 25.69]]),
 ... np.array([[1.01, 1.66, 3.5]]),
 ... 0.6
 ... )
 array([1.07173261, 1.65970737, 3.50160179])
 """
 ypred = local_weight_regression(training_data_x, mcol_b, tau)
 return ypred


def plot_preds(
 training_data_x: np.mat,
 predictions: np.ndarray,
 col_x: np.ndarray,
 col_y: np.ndarray,
 training_data_x: np.array,
 predictions: np.array,
 col_x: np.array,
 col_y: np.array,
 cola_name: str,
 colb_name: str,
) -> plt.plot:
 """
This function used to plot predictions and display the graph
Plot predictions and display the graph
 """
 xsort = training_data_x.copy()
 xsort.sort(axis=0)
Expand All@@ -128,6 +140,10 @@ def plot_preds(


if __name__ == "__main__":
 import doctest

 doctest.testmod()

 training_data_x, mcol_b, col_a, col_b = load_data("tips", "total_bill", "tip")
 predictions = get_preds(training_data_x, mcol_b, 0.5)
 plot_preds(training_data_x, predictions, col_a, col_b, "total_bill", "tip")

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Highlight search terms from Google/DuckDuckGo/Bing referrer\n(function() {\n var ref = document.referrer;\n var terms = [];\n \n if (ref.includes('google.com') || ref.includes('duckduckgo.com') || ref.includes('bing.com')) {\n var url = new URL(ref);\n var q = url.searchParams.get('q') || url.searchParams.get('p');\n if (q) {\n terms = q.split(/\\s+/).filter(function(t) { return t.length > 2; });\n }\n }\n \n if (terms.length === 0) return;\n \n var style = document.createElement('style');\n style.textContent = '.userscript-highlight { background: #fbbf24; color: #1a1a2e; padding: 1px 3px; border-radius: 2px; }';\n document.head.appendChild(style);\n \n function highlight(node) {\n if (node.nodeType === 3) { // text node\n var text = node.textContent;\n var found = false;\n terms.forEach(function(term) {\n var regex = new RegExp('(' + term.replace(/[.*+?^${}()|[\\]\\\\]/g, '\\\\') + ')', 'gi');\n if (regex.test(text)) {\n found = true;\n var frag = document.createDocumentFragment();\n var parts = text.split(regex);\n parts.forEach(function(part, i) {\n if (i % 2 === 0) {\n frag.appendChild(document.createTextNode(part));\n } else {\n var span = document.createElement('span');\n span.className = 'userscript-highlight';\n span.textContent = part;\n frag.appendChild(span);\n }\n });\n node.parentNode.replaceChild(frag, node);\n }\n });\n } else if (node.nodeType === 1 && node.childNodes) { // element\n var skipTags = ['SCRIPT', 'STYLE', 'NOSCRIPT', 'TEXTAREA', 'INPUT', 'SELECT'];\n if (!skipTags.includes(node.tagName)) {\n Array.from(node.childNodes).forEach(highlight);\n }\n }\n }\n \n highlight(document.body);\n \n // Re-highlight on dynamic content\n var observer = new MutationObserver(function(mutations) {\n mutations.forEach(function(m) {\n m.addedNodes.forEach(function(node) {\n if (node.nodeType === 1 || node.nodeType === 3) highlight(node);\n });\n });\n });\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "Highlight Search Terms");
}
} catch(__e) { console.warn('[Userscript:Highlight Search Terms]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
Refactor local_weighted_learning.py to use np.array#8069

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

cclauss
merged 4 commits into

from

Jan 2, 2023

+68

−51

 Merged


Refactor local_weighted_learning.py to use np.array#8069
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


4 commits


Select commit
Hold shift + click to select a range
f7ba9da

updating DIRECTORY.md

Jan 2, 2023
ac662b3

Format local_weighted_learning.py doctests for clarity


tianyizheng02 Jan 2, 2023
dae74a7

Refactor local_weighted_learning.py to use np.array instead of np.mat


tianyizheng02 Jan 2, 2023
8a1f929

Update local_weighted_learning.py documentation


tianyizheng02 Jan 2, 2023

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


3 changes: 2 additions & 1 deletion
DIRECTORY.md

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -123,6 +123,7 @@
 * [Huffman](compression/huffman.py)
 * [Lempel Ziv](compression/lempel_ziv.py)
 * [Lempel Ziv Decompress](compression/lempel_ziv_decompress.py)
 * [Lz77](compression/lz77.py)
 * [Peak Signal To Noise Ratio](compression/peak_signal_to_noise_ratio.py)
 * [Run Length Encoding](compression/run_length_encoding.py)

Expand DownExpand Up@@ -1162,7 +1163,7 @@
 * [Get Amazon Product Data](web_programming/get_amazon_product_data.py)
 * [Get Imdb Top 250 Movies Csv](web_programming/get_imdb_top_250_movies_csv.py)
 * [Get Imdbtop](web_programming/get_imdbtop.py)
 * [Get Top Billioners](web_programming/get_top_billioners.py)
 * [Get Top Billionaires](web_programming/get_top_billionaires.py)
 * [Get Top Hn Posts](web_programming/get_top_hn_posts.py)
 * [Get User Tweets](web_programming/get_user_tweets.py)
 * [Giphy](web_programming/giphy.py)
Expand Down

116 changes: 66 additions & 50 deletions
machine_learning/local_weighted_learning/local_weighted_learning.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -1,116 +1,128 @@
# Required imports to run this file
import matplotlib.pyplot as plt
import numpy as np


# weighted matrix
def weighted_matrix(point: np.mat, training_data_x: np.mat, bandwidth: float) -> np.mat:
def weighted_matrix(
 point: np.array, training_data_x: np.array, bandwidth: float
) -> np.array:
 """
 Calculate the weight for every point in the
 data set. It takes training_point , query_point, and tau
 Here Tau is not a fixed value it can be varied depends on output.
 tau --> bandwidth
 xmat -->Training data
 point --> the x where we want to make predictions
 >>> weighted_matrix(np.array([1., 1.]),np.mat([[16.99, 10.34], [21.01,23.68],
 ... [24.59,25.69]]), 0.6)
 matrix([[1.43807972e-207, 0.00000000e+000, 0.00000000e+000],
 [0.00000000e+000, 0.00000000e+000, 0.00000000e+000],
 [0.00000000e+000, 0.00000000e+000, 0.00000000e+000]])
 Calculate the weight for every point in the data set.
 point --> the x value at which we want to make predictions
 >>> weighted_matrix(
 ... np.array([1., 1.]),
 ... np.array([[16.99, 10.34], [21.01,23.68], [24.59,25.69]]),
 ... 0.6
 ... )
 array([[1.43807972e-207, 0.00000000e+000, 0.00000000e+000],
 [0.00000000e+000, 0.00000000e+000, 0.00000000e+000],
 [0.00000000e+000, 0.00000000e+000, 0.00000000e+000]])
 """
 # m is the number of training samples
 m, n = np.shape(training_data_x)
 # Initializing weights as identity matrix
 weights = np.mat(np.eye(m))
 m, _ = np.shape(training_data_x) # m is the number of training samples
 weights = np.eye(m) # Initializing weights as identity matrix

 # calculating weights for all training examples [x(i)'s]
 for j in range(m):
 diff = point - training_data_x[j]
 weights[j, j] = np.exp(diff * diff.T / (-2.0 * bandwidth**2))
 weights[j, j] = np.exp(diff @ diff.T / (-2.0 * bandwidth**2))
 return weights


def local_weight(
 point: np.mat, training_data_x: np.mat, training_data_y: np.mat, bandwidth: float
) -> np.mat:
 point: np.array,
 training_data_x: np.array,
 training_data_y: np.array,
 bandwidth: float,
) -> np.array:
 """
 Calculate the local weights using the weight_matrix function on training data.
 Return the weighted matrix.
 >>> local_weight(np.array([1., 1.]),np.mat([[16.99, 10.34], [21.01,23.68],
 ... [24.59,25.69]]),np.mat([[1.01, 1.66, 3.5]]), 0.6)
 matrix([[0.00873174],
 [0.08272556]])
 >>> local_weight(
 ... np.array([1., 1.]),
 ... np.array([[16.99, 10.34], [21.01,23.68], [24.59,25.69]]),
 ... np.array([[1.01, 1.66, 3.5]]),
 ... 0.6
 ... )
 array([[0.00873174],
 [0.08272556]])
 """
 weight = weighted_matrix(point, training_data_x, bandwidth)
 w = (training_data_x.T * (weight * training_data_x)).I * (
 training_data_x.T * weight * training_data_y.T
 w = np.linalg.inv(training_data_x.T @ (weight @ training_data_x)) @ (
 training_data_x.T @ weight @ training_data_y.T
 )

 return w


def local_weight_regression(
 training_data_x: np.mat, training_data_y: np.mat, bandwidth: float
) -> np.mat:
 training_data_x: np.array, training_data_y: np.array, bandwidth: float
) -> np.array:
 """
 Calculate predictions for each data point on axis.
 >>> local_weight_regression(np.mat([[16.99, 10.34], [21.01,23.68],
 ... [24.59,25.69]]),np.mat([[1.01, 1.66, 3.5]]), 0.6)
 Calculate predictions for each data point on axis
 >>> local_weight_regression(
 ... np.array([[16.99, 10.34], [21.01, 23.68], [24.59, 25.69]]),
 ... np.array([[1.01, 1.66, 3.5]]),
 ... 0.6
 ... )
 array([1.07173261, 1.65970737, 3.50160179])
 """
 m, n = np.shape(training_data_x)
 m, _ = np.shape(training_data_x)
 ypred = np.zeros(m)

 for i, item in enumerate(training_data_x):
 ypred[i] = item * local_weight(
 ypred[i] = item @ local_weight(
 item, training_data_x, training_data_y, bandwidth
 )

 return ypred


def load_data(dataset_name: str, cola_name: str, colb_name: str) -> np.mat:
def load_data(
 dataset_name: str, cola_name: str, colb_name: str
) -> tuple[np.array, np.array, np.array, np.array]:
 """
Function used for loading data from the seaborn splitting into x and y points
Load data from seaborn and split it into x and y points
 """
 import seaborn as sns

 data = sns.load_dataset(dataset_name)
 col_a = np.array(data[cola_name]) # total_bill
 col_b = np.array(data[colb_name]) # tip

 mcol_a = np.mat(col_a)
 mcol_b = np.mat(col_b)
 mcol_a = col_a.copy()
 mcol_b = col_b.copy()

 m = np.shape(mcol_b)[1]
 one = np.ones((1, m), dtype=int)
 one = np.ones(np.shape(mcol_b)[0], dtype=int)

 # horizontal stacking
 training_data_x = np.hstack((one.T, mcol_a.T))
 # pairing elements of one and mcol_a
 training_data_x = np.column_stack((one, mcol_a))

 return training_data_x, mcol_b, col_a, col_b


def get_preds(training_data_x: np.mat, mcol_b: np.mat, tau: float) -> np.ndarray:
def get_preds(training_data_x: np.array, mcol_b: np.array, tau: float) -> np.array:
 """
 Get predictions with minimum error for each training data
 >>> get_preds(np.mat([[16.99, 10.34], [21.01,23.68],
 ... [24.59,25.69]]),np.mat([[1.01, 1.66, 3.5]]), 0.6)
 >>> get_preds(
 ... np.array([[16.99, 10.34], [21.01, 23.68], [24.59, 25.69]]),
 ... np.array([[1.01, 1.66, 3.5]]),
 ... 0.6
 ... )
 array([1.07173261, 1.65970737, 3.50160179])
 """
 ypred = local_weight_regression(training_data_x, mcol_b, tau)
 return ypred


def plot_preds(
 training_data_x: np.mat,
 predictions: np.ndarray,
 col_x: np.ndarray,
 col_y: np.ndarray,
 training_data_x: np.array,
 predictions: np.array,
 col_x: np.array,
 col_y: np.array,
 cola_name: str,
 colb_name: str,
) -> plt.plot:
 """
This function used to plot predictions and display the graph
Plot predictions and display the graph
 """
 xsort = training_data_x.copy()
 xsort.sort(axis=0)
Expand All@@ -128,6 +140,10 @@ def plot_preds(


if __name__ == "__main__":
 import doctest

 doctest.testmod()

 training_data_x, mcol_b, col_a, col_b = load_data("tips", "total_bill", "tip")
 predictions = get_preds(training_data_x, mcol_b, 0.5)
 plot_preds(training_data_x, predictions, col_a, col_b, "total_bill", "tip")

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Strip utm_, fbclid, gclid, etc. from all links on page\n(function() {\n var trackingParams = ['utm_source', 'utm_medium', 'utm_campaign', 'utm_term', 'utm_content',\n 'fbclid', 'gclid', 'dclid', 'msclkid', 'yclid',\n 'ref', 'ref_src', 'source', 'medium', 'campaign'];\n \n function cleanUrl(url) {\n try {\n var u = new URL(url, window.location.origin);\n var changed = false;\n trackingParams.forEach(function(p) {\n if (u.searchParams.has(p)) {\n u.searchParams.delete(p);\n changed = true;\n }\n });\n return changed ? u.toString() : url;\n } catch (e) {\n return url;\n }\n }\n \n function cleanLinks() {\n document.querySelectorAll('a[href]').forEach(function(a) {\n var clean = cleanUrl(a.href);\n if (clean !== a.href) a.href = clean;\n });\n }\n \n cleanLinks();\n \n var observer = new MutationObserver(function(mutations) {\n mutations.forEach(function(m) {\n m.addedNodes.forEach(function(node) {\n if (node.nodeType === 1) {\n if (node.tagName === 'A') cleanLinks();\n node.querySelectorAll('a[href]').forEach(function(a) {\n var clean = cleanUrl(a.href);\n if (clean !== a.href) a.href = clean;\n });\n }\n });\n });\n });\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "Remove Tracking Parameters from Links");
}
} catch(__e) { console.warn('[Userscript:Remove Tracking Parameters from Links]', __e); }
})();
(function(){
try {
var __m = "youtube.com";
var __re = new RegExp('^' + "youtube\\.com" + '

Skip to content
Refactor local_weighted_learning.py to use np.array#8069

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

cclauss
merged 4 commits into

from

Jan 2, 2023

+68

−51

 Merged


Refactor local_weighted_learning.py to use np.array#8069
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


4 commits


Select commit
Hold shift + click to select a range
f7ba9da

updating DIRECTORY.md

Jan 2, 2023
ac662b3

Format local_weighted_learning.py doctests for clarity


tianyizheng02 Jan 2, 2023
dae74a7

Refactor local_weighted_learning.py to use np.array instead of np.mat


tianyizheng02 Jan 2, 2023
8a1f929

Update local_weighted_learning.py documentation


tianyizheng02 Jan 2, 2023

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


3 changes: 2 additions & 1 deletion
DIRECTORY.md

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -123,6 +123,7 @@
 * [Huffman](compression/huffman.py)
 * [Lempel Ziv](compression/lempel_ziv.py)
 * [Lempel Ziv Decompress](compression/lempel_ziv_decompress.py)
 * [Lz77](compression/lz77.py)
 * [Peak Signal To Noise Ratio](compression/peak_signal_to_noise_ratio.py)
 * [Run Length Encoding](compression/run_length_encoding.py)

Expand DownExpand Up@@ -1162,7 +1163,7 @@
 * [Get Amazon Product Data](web_programming/get_amazon_product_data.py)
 * [Get Imdb Top 250 Movies Csv](web_programming/get_imdb_top_250_movies_csv.py)
 * [Get Imdbtop](web_programming/get_imdbtop.py)
 * [Get Top Billioners](web_programming/get_top_billioners.py)
 * [Get Top Billionaires](web_programming/get_top_billionaires.py)
 * [Get Top Hn Posts](web_programming/get_top_hn_posts.py)
 * [Get User Tweets](web_programming/get_user_tweets.py)
 * [Giphy](web_programming/giphy.py)
Expand Down

116 changes: 66 additions & 50 deletions
machine_learning/local_weighted_learning/local_weighted_learning.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -1,116 +1,128 @@
# Required imports to run this file
import matplotlib.pyplot as plt
import numpy as np


# weighted matrix
def weighted_matrix(point: np.mat, training_data_x: np.mat, bandwidth: float) -> np.mat:
def weighted_matrix(
 point: np.array, training_data_x: np.array, bandwidth: float
) -> np.array:
 """
 Calculate the weight for every point in the
 data set. It takes training_point , query_point, and tau
 Here Tau is not a fixed value it can be varied depends on output.
 tau --> bandwidth
 xmat -->Training data
 point --> the x where we want to make predictions
 >>> weighted_matrix(np.array([1., 1.]),np.mat([[16.99, 10.34], [21.01,23.68],
 ... [24.59,25.69]]), 0.6)
 matrix([[1.43807972e-207, 0.00000000e+000, 0.00000000e+000],
 [0.00000000e+000, 0.00000000e+000, 0.00000000e+000],
 [0.00000000e+000, 0.00000000e+000, 0.00000000e+000]])
 Calculate the weight for every point in the data set.
 point --> the x value at which we want to make predictions
 >>> weighted_matrix(
 ... np.array([1., 1.]),
 ... np.array([[16.99, 10.34], [21.01,23.68], [24.59,25.69]]),
 ... 0.6
 ... )
 array([[1.43807972e-207, 0.00000000e+000, 0.00000000e+000],
 [0.00000000e+000, 0.00000000e+000, 0.00000000e+000],
 [0.00000000e+000, 0.00000000e+000, 0.00000000e+000]])
 """
 # m is the number of training samples
 m, n = np.shape(training_data_x)
 # Initializing weights as identity matrix
 weights = np.mat(np.eye(m))
 m, _ = np.shape(training_data_x) # m is the number of training samples
 weights = np.eye(m) # Initializing weights as identity matrix

 # calculating weights for all training examples [x(i)'s]
 for j in range(m):
 diff = point - training_data_x[j]
 weights[j, j] = np.exp(diff * diff.T / (-2.0 * bandwidth**2))
 weights[j, j] = np.exp(diff @ diff.T / (-2.0 * bandwidth**2))
 return weights


def local_weight(
 point: np.mat, training_data_x: np.mat, training_data_y: np.mat, bandwidth: float
) -> np.mat:
 point: np.array,
 training_data_x: np.array,
 training_data_y: np.array,
 bandwidth: float,
) -> np.array:
 """
 Calculate the local weights using the weight_matrix function on training data.
 Return the weighted matrix.
 >>> local_weight(np.array([1., 1.]),np.mat([[16.99, 10.34], [21.01,23.68],
 ... [24.59,25.69]]),np.mat([[1.01, 1.66, 3.5]]), 0.6)
 matrix([[0.00873174],
 [0.08272556]])
 >>> local_weight(
 ... np.array([1., 1.]),
 ... np.array([[16.99, 10.34], [21.01,23.68], [24.59,25.69]]),
 ... np.array([[1.01, 1.66, 3.5]]),
 ... 0.6
 ... )
 array([[0.00873174],
 [0.08272556]])
 """
 weight = weighted_matrix(point, training_data_x, bandwidth)
 w = (training_data_x.T * (weight * training_data_x)).I * (
 training_data_x.T * weight * training_data_y.T
 w = np.linalg.inv(training_data_x.T @ (weight @ training_data_x)) @ (
 training_data_x.T @ weight @ training_data_y.T
 )

 return w


def local_weight_regression(
 training_data_x: np.mat, training_data_y: np.mat, bandwidth: float
) -> np.mat:
 training_data_x: np.array, training_data_y: np.array, bandwidth: float
) -> np.array:
 """
 Calculate predictions for each data point on axis.
 >>> local_weight_regression(np.mat([[16.99, 10.34], [21.01,23.68],
 ... [24.59,25.69]]),np.mat([[1.01, 1.66, 3.5]]), 0.6)
 Calculate predictions for each data point on axis
 >>> local_weight_regression(
 ... np.array([[16.99, 10.34], [21.01, 23.68], [24.59, 25.69]]),
 ... np.array([[1.01, 1.66, 3.5]]),
 ... 0.6
 ... )
 array([1.07173261, 1.65970737, 3.50160179])
 """
 m, n = np.shape(training_data_x)
 m, _ = np.shape(training_data_x)
 ypred = np.zeros(m)

 for i, item in enumerate(training_data_x):
 ypred[i] = item * local_weight(
 ypred[i] = item @ local_weight(
 item, training_data_x, training_data_y, bandwidth
 )

 return ypred


def load_data(dataset_name: str, cola_name: str, colb_name: str) -> np.mat:
def load_data(
 dataset_name: str, cola_name: str, colb_name: str
) -> tuple[np.array, np.array, np.array, np.array]:
 """
Function used for loading data from the seaborn splitting into x and y points
Load data from seaborn and split it into x and y points
 """
 import seaborn as sns

 data = sns.load_dataset(dataset_name)
 col_a = np.array(data[cola_name]) # total_bill
 col_b = np.array(data[colb_name]) # tip

 mcol_a = np.mat(col_a)
 mcol_b = np.mat(col_b)
 mcol_a = col_a.copy()
 mcol_b = col_b.copy()

 m = np.shape(mcol_b)[1]
 one = np.ones((1, m), dtype=int)
 one = np.ones(np.shape(mcol_b)[0], dtype=int)

 # horizontal stacking
 training_data_x = np.hstack((one.T, mcol_a.T))
 # pairing elements of one and mcol_a
 training_data_x = np.column_stack((one, mcol_a))

 return training_data_x, mcol_b, col_a, col_b


def get_preds(training_data_x: np.mat, mcol_b: np.mat, tau: float) -> np.ndarray:
def get_preds(training_data_x: np.array, mcol_b: np.array, tau: float) -> np.array:
 """
 Get predictions with minimum error for each training data
 >>> get_preds(np.mat([[16.99, 10.34], [21.01,23.68],
 ... [24.59,25.69]]),np.mat([[1.01, 1.66, 3.5]]), 0.6)
 >>> get_preds(
 ... np.array([[16.99, 10.34], [21.01, 23.68], [24.59, 25.69]]),
 ... np.array([[1.01, 1.66, 3.5]]),
 ... 0.6
 ... )
 array([1.07173261, 1.65970737, 3.50160179])
 """
 ypred = local_weight_regression(training_data_x, mcol_b, tau)
 return ypred


def plot_preds(
 training_data_x: np.mat,
 predictions: np.ndarray,
 col_x: np.ndarray,
 col_y: np.ndarray,
 training_data_x: np.array,
 predictions: np.array,
 col_x: np.array,
 col_y: np.array,
 cola_name: str,
 colb_name: str,
) -> plt.plot:
 """
This function used to plot predictions and display the graph
Plot predictions and display the graph
 """
 xsort = training_data_x.copy()
 xsort.sort(axis=0)
Expand All@@ -128,6 +140,10 @@ def plot_preds(


if __name__ == "__main__":
 import doctest

 doctest.testmod()

 training_data_x, mcol_b, col_a, col_b = load_data("tips", "total_bill", "tip")
 predictions = get_preds(training_data_x, mcol_b, 0.5)
 plot_preds(training_data_x, predictions, col_a, col_b, "total_bill", "tip")

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Auto-enable theater mode on YouTube\n(function() {\n function tryTheater() {\n var btn = document.querySelector('button[aria-label=\"Theater mode\"], ytd-player #player button[title=\"Theater mode\"]');\n if (btn && !btn.classList.contains('activated')) {\n btn.click();\n }\n }\n \n // Try immediately\n tryTheater();\n \n // Try after navigation (SPA)\n var lastUrl = location.href;\n setInterval(function() {\n if (location.href !== lastUrl) {\n lastUrl = location.href;\n setTimeout(tryTheater, 500);\n }\n }, 1000);\n \n // Also try on player load\n var observer = new MutationObserver(tryTheater);\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "YouTube Theater Mode Default");
}
} catch(__e) { console.warn('[Userscript:YouTube Theater Mode Default]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
Refactor local_weighted_learning.py to use np.array#8069

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

cclauss
merged 4 commits into

from

Jan 2, 2023

+68

−51

 Merged


Refactor local_weighted_learning.py to use np.array#8069
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


4 commits


Select commit
Hold shift + click to select a range
f7ba9da

updating DIRECTORY.md

Jan 2, 2023
ac662b3

Format local_weighted_learning.py doctests for clarity


tianyizheng02 Jan 2, 2023
dae74a7

Refactor local_weighted_learning.py to use np.array instead of np.mat


tianyizheng02 Jan 2, 2023
8a1f929

Update local_weighted_learning.py documentation


tianyizheng02 Jan 2, 2023

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


3 changes: 2 additions & 1 deletion
DIRECTORY.md

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -123,6 +123,7 @@
 * [Huffman](compression/huffman.py)
 * [Lempel Ziv](compression/lempel_ziv.py)
 * [Lempel Ziv Decompress](compression/lempel_ziv_decompress.py)
 * [Lz77](compression/lz77.py)
 * [Peak Signal To Noise Ratio](compression/peak_signal_to_noise_ratio.py)
 * [Run Length Encoding](compression/run_length_encoding.py)

Expand DownExpand Up@@ -1162,7 +1163,7 @@
 * [Get Amazon Product Data](web_programming/get_amazon_product_data.py)
 * [Get Imdb Top 250 Movies Csv](web_programming/get_imdb_top_250_movies_csv.py)
 * [Get Imdbtop](web_programming/get_imdbtop.py)
 * [Get Top Billioners](web_programming/get_top_billioners.py)
 * [Get Top Billionaires](web_programming/get_top_billionaires.py)
 * [Get Top Hn Posts](web_programming/get_top_hn_posts.py)
 * [Get User Tweets](web_programming/get_user_tweets.py)
 * [Giphy](web_programming/giphy.py)
Expand Down

116 changes: 66 additions & 50 deletions
machine_learning/local_weighted_learning/local_weighted_learning.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -1,116 +1,128 @@
# Required imports to run this file
import matplotlib.pyplot as plt
import numpy as np


# weighted matrix
def weighted_matrix(point: np.mat, training_data_x: np.mat, bandwidth: float) -> np.mat:
def weighted_matrix(
 point: np.array, training_data_x: np.array, bandwidth: float
) -> np.array:
 """
 Calculate the weight for every point in the
 data set. It takes training_point , query_point, and tau
 Here Tau is not a fixed value it can be varied depends on output.
 tau --> bandwidth
 xmat -->Training data
 point --> the x where we want to make predictions
 >>> weighted_matrix(np.array([1., 1.]),np.mat([[16.99, 10.34], [21.01,23.68],
 ... [24.59,25.69]]), 0.6)
 matrix([[1.43807972e-207, 0.00000000e+000, 0.00000000e+000],
 [0.00000000e+000, 0.00000000e+000, 0.00000000e+000],
 [0.00000000e+000, 0.00000000e+000, 0.00000000e+000]])
 Calculate the weight for every point in the data set.
 point --> the x value at which we want to make predictions
 >>> weighted_matrix(
 ... np.array([1., 1.]),
 ... np.array([[16.99, 10.34], [21.01,23.68], [24.59,25.69]]),
 ... 0.6
 ... )
 array([[1.43807972e-207, 0.00000000e+000, 0.00000000e+000],
 [0.00000000e+000, 0.00000000e+000, 0.00000000e+000],
 [0.00000000e+000, 0.00000000e+000, 0.00000000e+000]])
 """
 # m is the number of training samples
 m, n = np.shape(training_data_x)
 # Initializing weights as identity matrix
 weights = np.mat(np.eye(m))
 m, _ = np.shape(training_data_x) # m is the number of training samples
 weights = np.eye(m) # Initializing weights as identity matrix

 # calculating weights for all training examples [x(i)'s]
 for j in range(m):
 diff = point - training_data_x[j]
 weights[j, j] = np.exp(diff * diff.T / (-2.0 * bandwidth**2))
 weights[j, j] = np.exp(diff @ diff.T / (-2.0 * bandwidth**2))
 return weights


def local_weight(
 point: np.mat, training_data_x: np.mat, training_data_y: np.mat, bandwidth: float
) -> np.mat:
 point: np.array,
 training_data_x: np.array,
 training_data_y: np.array,
 bandwidth: float,
) -> np.array:
 """
 Calculate the local weights using the weight_matrix function on training data.
 Return the weighted matrix.
 >>> local_weight(np.array([1., 1.]),np.mat([[16.99, 10.34], [21.01,23.68],
 ... [24.59,25.69]]),np.mat([[1.01, 1.66, 3.5]]), 0.6)
 matrix([[0.00873174],
 [0.08272556]])
 >>> local_weight(
 ... np.array([1., 1.]),
 ... np.array([[16.99, 10.34], [21.01,23.68], [24.59,25.69]]),
 ... np.array([[1.01, 1.66, 3.5]]),
 ... 0.6
 ... )
 array([[0.00873174],
 [0.08272556]])
 """
 weight = weighted_matrix(point, training_data_x, bandwidth)
 w = (training_data_x.T * (weight * training_data_x)).I * (
 training_data_x.T * weight * training_data_y.T
 w = np.linalg.inv(training_data_x.T @ (weight @ training_data_x)) @ (
 training_data_x.T @ weight @ training_data_y.T
 )

 return w


def local_weight_regression(
 training_data_x: np.mat, training_data_y: np.mat, bandwidth: float
) -> np.mat:
 training_data_x: np.array, training_data_y: np.array, bandwidth: float
) -> np.array:
 """
 Calculate predictions for each data point on axis.
 >>> local_weight_regression(np.mat([[16.99, 10.34], [21.01,23.68],
 ... [24.59,25.69]]),np.mat([[1.01, 1.66, 3.5]]), 0.6)
 Calculate predictions for each data point on axis
 >>> local_weight_regression(
 ... np.array([[16.99, 10.34], [21.01, 23.68], [24.59, 25.69]]),
 ... np.array([[1.01, 1.66, 3.5]]),
 ... 0.6
 ... )
 array([1.07173261, 1.65970737, 3.50160179])
 """
 m, n = np.shape(training_data_x)
 m, _ = np.shape(training_data_x)
 ypred = np.zeros(m)

 for i, item in enumerate(training_data_x):
 ypred[i] = item * local_weight(
 ypred[i] = item @ local_weight(
 item, training_data_x, training_data_y, bandwidth
 )

 return ypred


def load_data(dataset_name: str, cola_name: str, colb_name: str) -> np.mat:
def load_data(
 dataset_name: str, cola_name: str, colb_name: str
) -> tuple[np.array, np.array, np.array, np.array]:
 """
Function used for loading data from the seaborn splitting into x and y points
Load data from seaborn and split it into x and y points
 """
 import seaborn as sns

 data = sns.load_dataset(dataset_name)
 col_a = np.array(data[cola_name]) # total_bill
 col_b = np.array(data[colb_name]) # tip

 mcol_a = np.mat(col_a)
 mcol_b = np.mat(col_b)
 mcol_a = col_a.copy()
 mcol_b = col_b.copy()

 m = np.shape(mcol_b)[1]
 one = np.ones((1, m), dtype=int)
 one = np.ones(np.shape(mcol_b)[0], dtype=int)

 # horizontal stacking
 training_data_x = np.hstack((one.T, mcol_a.T))
 # pairing elements of one and mcol_a
 training_data_x = np.column_stack((one, mcol_a))

 return training_data_x, mcol_b, col_a, col_b


def get_preds(training_data_x: np.mat, mcol_b: np.mat, tau: float) -> np.ndarray:
def get_preds(training_data_x: np.array, mcol_b: np.array, tau: float) -> np.array:
 """
 Get predictions with minimum error for each training data
 >>> get_preds(np.mat([[16.99, 10.34], [21.01,23.68],
 ... [24.59,25.69]]),np.mat([[1.01, 1.66, 3.5]]), 0.6)
 >>> get_preds(
 ... np.array([[16.99, 10.34], [21.01, 23.68], [24.59, 25.69]]),
 ... np.array([[1.01, 1.66, 3.5]]),
 ... 0.6
 ... )
 array([1.07173261, 1.65970737, 3.50160179])
 """
 ypred = local_weight_regression(training_data_x, mcol_b, tau)
 return ypred


def plot_preds(
 training_data_x: np.mat,
 predictions: np.ndarray,
 col_x: np.ndarray,
 col_y: np.ndarray,
 training_data_x: np.array,
 predictions: np.array,
 col_x: np.array,
 col_y: np.array,
 cola_name: str,
 colb_name: str,
) -> plt.plot:
 """
This function used to plot predictions and display the graph
Plot predictions and display the graph
 """
 xsort = training_data_x.copy()
 xsort.sort(axis=0)
Expand All@@ -128,6 +140,10 @@ def plot_preds(


if __name__ == "__main__":
 import doctest

 doctest.testmod()

 training_data_x, mcol_b, col_a, col_b = load_data("tips", "total_bill", "tip")
 predictions = get_preds(training_data_x, mcol_b, 0.5)
 plot_preds(training_data_x, predictions, col_a, col_b, "total_bill", "tip")

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Remove or un-stick sticky/fixed headers that block content\n(function() {\n function unstick() {\n document.querySelectorAll('header, nav, [role=\"banner\"], .header, .navbar, .sticky, .fixed-top, [style*=\"position: fixed\"], [style*=\"position:sticky\"]').forEach(function(el) {\n if (el.style.position === 'fixed' || el.style.position === 'sticky' || \n getComputedStyle(el).position === 'fixed' || getComputedStyle(el).position === 'sticky') {\n el.style.position = 'static';\n el.style.top = 'auto';\n el.style.zIndex = 'auto';\n }\n });\n }\n \n unstick();\n \n var observer = new MutationObserver(unstick);\n observer.observe(document.body, { childList: true, subtree: true, attributes: true, attributeFilter: ['style', 'class'] });\n})();", "Kill Sticky Headers");
}
} catch(__e) { console.warn('[Userscript:Kill Sticky Headers]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
Refactor local_weighted_learning.py to use np.array#8069

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

cclauss
merged 4 commits into

from

Jan 2, 2023

+68

−51

 Merged


Refactor local_weighted_learning.py to use np.array#8069
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


4 commits


Select commit
Hold shift + click to select a range
f7ba9da

updating DIRECTORY.md

Jan 2, 2023
ac662b3

Format local_weighted_learning.py doctests for clarity


tianyizheng02 Jan 2, 2023
dae74a7

Refactor local_weighted_learning.py to use np.array instead of np.mat


tianyizheng02 Jan 2, 2023
8a1f929

Update local_weighted_learning.py documentation


tianyizheng02 Jan 2, 2023

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


3 changes: 2 additions & 1 deletion
DIRECTORY.md

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -123,6 +123,7 @@
 * [Huffman](compression/huffman.py)
 * [Lempel Ziv](compression/lempel_ziv.py)
 * [Lempel Ziv Decompress](compression/lempel_ziv_decompress.py)
 * [Lz77](compression/lz77.py)
 * [Peak Signal To Noise Ratio](compression/peak_signal_to_noise_ratio.py)
 * [Run Length Encoding](compression/run_length_encoding.py)

Expand DownExpand Up@@ -1162,7 +1163,7 @@
 * [Get Amazon Product Data](web_programming/get_amazon_product_data.py)
 * [Get Imdb Top 250 Movies Csv](web_programming/get_imdb_top_250_movies_csv.py)
 * [Get Imdbtop](web_programming/get_imdbtop.py)
 * [Get Top Billioners](web_programming/get_top_billioners.py)
 * [Get Top Billionaires](web_programming/get_top_billionaires.py)
 * [Get Top Hn Posts](web_programming/get_top_hn_posts.py)
 * [Get User Tweets](web_programming/get_user_tweets.py)
 * [Giphy](web_programming/giphy.py)
Expand Down

116 changes: 66 additions & 50 deletions
machine_learning/local_weighted_learning/local_weighted_learning.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -1,116 +1,128 @@
# Required imports to run this file
import matplotlib.pyplot as plt
import numpy as np


# weighted matrix
def weighted_matrix(point: np.mat, training_data_x: np.mat, bandwidth: float) -> np.mat:
def weighted_matrix(
 point: np.array, training_data_x: np.array, bandwidth: float
) -> np.array:
 """
 Calculate the weight for every point in the
 data set. It takes training_point , query_point, and tau
 Here Tau is not a fixed value it can be varied depends on output.
 tau --> bandwidth
 xmat -->Training data
 point --> the x where we want to make predictions
 >>> weighted_matrix(np.array([1., 1.]),np.mat([[16.99, 10.34], [21.01,23.68],
 ... [24.59,25.69]]), 0.6)
 matrix([[1.43807972e-207, 0.00000000e+000, 0.00000000e+000],
 [0.00000000e+000, 0.00000000e+000, 0.00000000e+000],
 [0.00000000e+000, 0.00000000e+000, 0.00000000e+000]])
 Calculate the weight for every point in the data set.
 point --> the x value at which we want to make predictions
 >>> weighted_matrix(
 ... np.array([1., 1.]),
 ... np.array([[16.99, 10.34], [21.01,23.68], [24.59,25.69]]),
 ... 0.6
 ... )
 array([[1.43807972e-207, 0.00000000e+000, 0.00000000e+000],
 [0.00000000e+000, 0.00000000e+000, 0.00000000e+000],
 [0.00000000e+000, 0.00000000e+000, 0.00000000e+000]])
 """
 # m is the number of training samples
 m, n = np.shape(training_data_x)
 # Initializing weights as identity matrix
 weights = np.mat(np.eye(m))
 m, _ = np.shape(training_data_x) # m is the number of training samples
 weights = np.eye(m) # Initializing weights as identity matrix

 # calculating weights for all training examples [x(i)'s]
 for j in range(m):
 diff = point - training_data_x[j]
 weights[j, j] = np.exp(diff * diff.T / (-2.0 * bandwidth**2))
 weights[j, j] = np.exp(diff @ diff.T / (-2.0 * bandwidth**2))
 return weights


def local_weight(
 point: np.mat, training_data_x: np.mat, training_data_y: np.mat, bandwidth: float
) -> np.mat:
 point: np.array,
 training_data_x: np.array,
 training_data_y: np.array,
 bandwidth: float,
) -> np.array:
 """
 Calculate the local weights using the weight_matrix function on training data.
 Return the weighted matrix.
 >>> local_weight(np.array([1., 1.]),np.mat([[16.99, 10.34], [21.01,23.68],
 ... [24.59,25.69]]),np.mat([[1.01, 1.66, 3.5]]), 0.6)
 matrix([[0.00873174],
 [0.08272556]])
 >>> local_weight(
 ... np.array([1., 1.]),
 ... np.array([[16.99, 10.34], [21.01,23.68], [24.59,25.69]]),
 ... np.array([[1.01, 1.66, 3.5]]),
 ... 0.6
 ... )
 array([[0.00873174],
 [0.08272556]])
 """
 weight = weighted_matrix(point, training_data_x, bandwidth)
 w = (training_data_x.T * (weight * training_data_x)).I * (
 training_data_x.T * weight * training_data_y.T
 w = np.linalg.inv(training_data_x.T @ (weight @ training_data_x)) @ (
 training_data_x.T @ weight @ training_data_y.T
 )

 return w


def local_weight_regression(
 training_data_x: np.mat, training_data_y: np.mat, bandwidth: float
) -> np.mat:
 training_data_x: np.array, training_data_y: np.array, bandwidth: float
) -> np.array:
 """
 Calculate predictions for each data point on axis.
 >>> local_weight_regression(np.mat([[16.99, 10.34], [21.01,23.68],
 ... [24.59,25.69]]),np.mat([[1.01, 1.66, 3.5]]), 0.6)
 Calculate predictions for each data point on axis
 >>> local_weight_regression(
 ... np.array([[16.99, 10.34], [21.01, 23.68], [24.59, 25.69]]),
 ... np.array([[1.01, 1.66, 3.5]]),
 ... 0.6
 ... )
 array([1.07173261, 1.65970737, 3.50160179])
 """
 m, n = np.shape(training_data_x)
 m, _ = np.shape(training_data_x)
 ypred = np.zeros(m)

 for i, item in enumerate(training_data_x):
 ypred[i] = item * local_weight(
 ypred[i] = item @ local_weight(
 item, training_data_x, training_data_y, bandwidth
 )

 return ypred


def load_data(dataset_name: str, cola_name: str, colb_name: str) -> np.mat:
def load_data(
 dataset_name: str, cola_name: str, colb_name: str
) -> tuple[np.array, np.array, np.array, np.array]:
 """
Function used for loading data from the seaborn splitting into x and y points
Load data from seaborn and split it into x and y points
 """
 import seaborn as sns

 data = sns.load_dataset(dataset_name)
 col_a = np.array(data[cola_name]) # total_bill
 col_b = np.array(data[colb_name]) # tip

 mcol_a = np.mat(col_a)
 mcol_b = np.mat(col_b)
 mcol_a = col_a.copy()
 mcol_b = col_b.copy()

 m = np.shape(mcol_b)[1]
 one = np.ones((1, m), dtype=int)
 one = np.ones(np.shape(mcol_b)[0], dtype=int)

 # horizontal stacking
 training_data_x = np.hstack((one.T, mcol_a.T))
 # pairing elements of one and mcol_a
 training_data_x = np.column_stack((one, mcol_a))

 return training_data_x, mcol_b, col_a, col_b


def get_preds(training_data_x: np.mat, mcol_b: np.mat, tau: float) -> np.ndarray:
def get_preds(training_data_x: np.array, mcol_b: np.array, tau: float) -> np.array:
 """
 Get predictions with minimum error for each training data
 >>> get_preds(np.mat([[16.99, 10.34], [21.01,23.68],
 ... [24.59,25.69]]),np.mat([[1.01, 1.66, 3.5]]), 0.6)
 >>> get_preds(
 ... np.array([[16.99, 10.34], [21.01, 23.68], [24.59, 25.69]]),
 ... np.array([[1.01, 1.66, 3.5]]),
 ... 0.6
 ... )
 array([1.07173261, 1.65970737, 3.50160179])
 """
 ypred = local_weight_regression(training_data_x, mcol_b, tau)
 return ypred


def plot_preds(
 training_data_x: np.mat,
 predictions: np.ndarray,
 col_x: np.ndarray,
 col_y: np.ndarray,
 training_data_x: np.array,
 predictions: np.array,
 col_x: np.array,
 col_y: np.array,
 cola_name: str,
 colb_name: str,
) -> plt.plot:
 """
This function used to plot predictions and display the graph
Plot predictions and display the graph
 """
 xsort = training_data_x.copy()
 xsort.sort(axis=0)
Expand All@@ -128,6 +140,10 @@ def plot_preds(


if __name__ == "__main__":
 import doctest

 doctest.testmod()

 training_data_x, mcol_b, col_a, col_b = load_data("tips", "total_bill", "tip")
 predictions = get_preds(training_data_x, mcol_b, 0.5)
 plot_preds(training_data_x, predictions, col_a, col_b, "total_bill", "tip")

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Universal Dark Mode - works on any site\n(function() {\n var enabled = true;\n \n function applyDarkMode() {\n if (!enabled) return;\n \n // Create style element if it doesn't exist\n var style = document.getElementById('universal-dark-mode-style');\n if (!style) {\n style = document.createElement('style');\n style.id = 'universal-dark-mode-style';\n document.head.appendChild(style);\n }\n \n // Dark mode CSS - inverts colors but preserves images/video\n style.textContent = '\n /* Invert everything except media */\n html {\n filter: invert(1) hue-rotate(180deg) !important;\n background: #1a1a2e !important;\n }\n \n /* Restore images, videos, iframes, canvas */\n img, video, iframe, canvas, svg, picture, [style*=\"background-image\"] {\n filter: invert(1) hue-rotate(180deg) !important;\n }\n \n /* Preserve specific elements that should not be inverted */\n .no-dark-mode, .no-dark-mode *,\n [data-theme=\"light\"], [data-theme=\"light\"],\n .ace_editor, .ace_editor *,\n .CodeMirror, .CodeMirror *,\n .monaco-editor, .monaco-editor *,\n .markdown-body pre, .markdown-body pre *,\n .highlight, .highlight *,\n pre code, pre code * {\n filter: none !important;\n }\n \n /* Fix common UI elements */\n .modal, .popup, .dropdown-menu, .tooltip, .popover {\n filter: invert(1) hue-rotate(180deg) !important;\n background: #2d2d44 !important;\n border-color: #444 !important;\n }\n \n /* Scrollbars */\n ::-webkit-scrollbar { background: #1a1a2e !important; }\n ::-webkit-scrollbar-thumb { background: #444 !important; }\n ::-webkit-scrollbar-thumb:hover { background: #555 !important; }\n \n /* Selection */\n ::selection { background: #4ecdc4 !important; color: #1a1a2e !important; }\n ::-moz-selection { background: #4ecdc4 !important; color: #1a1a2e !important; }\n ';\n }\n \n function removeDarkMode() {\n var style = document.getElementById('universal-dark-mode-style');\n if (style) style.remove();\n }\n \n // Toggle with Alt+Shift+D\n document.addEventListener('keydown', function(e) {\n if (e.altKey && e.shiftKey && e.key === 'D') {\n e.preventDefault();\n enabled = !enabled;\n if (enabled) {\n applyDarkMode();\n console.log('[Universal Dark Mode] Enabled');\n } else {\n removeDarkMode();\n console.log('[Universal Dark Mode] Disabled');\n }\n }\n });\n \n // Apply on load\n applyDarkMode();\n \n // Re-apply on dynamic content\n var observer = new MutationObserver(function(mutations) {\n if (enabled && !document.getElementById('universal-dark-mode-style')) {\n applyDarkMode();\n }\n });\n observer.observe(document.head, { childList: true });\n \n console.log('[Universal Dark Mode] Loaded - Press Alt+Shift+D to toggle');\n})();", "Universal Dark Mode");
}
} catch(__e) { console.warn('[Userscript:Universal Dark Mode]', __e); }
})();
})();

Skip to content
Refactor local_weighted_learning.py to use np.array#8069

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

cclauss
merged 4 commits into

from

Jan 2, 2023

+68

−51

 Merged


Refactor local_weighted_learning.py to use np.array#8069
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


4 commits


Select commit
Hold shift + click to select a range
f7ba9da

updating DIRECTORY.md

Jan 2, 2023
ac662b3

Format local_weighted_learning.py doctests for clarity


tianyizheng02 Jan 2, 2023
dae74a7

Refactor local_weighted_learning.py to use np.array instead of np.mat


tianyizheng02 Jan 2, 2023
8a1f929

Update local_weighted_learning.py documentation


tianyizheng02 Jan 2, 2023

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


3 changes: 2 additions & 1 deletion
DIRECTORY.md

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -123,6 +123,7 @@
 * [Huffman](compression/huffman.py)
 * [Lempel Ziv](compression/lempel_ziv.py)
 * [Lempel Ziv Decompress](compression/lempel_ziv_decompress.py)
 * [Lz77](compression/lz77.py)
 * [Peak Signal To Noise Ratio](compression/peak_signal_to_noise_ratio.py)
 * [Run Length Encoding](compression/run_length_encoding.py)

Expand DownExpand Up@@ -1162,7 +1163,7 @@
 * [Get Amazon Product Data](web_programming/get_amazon_product_data.py)
 * [Get Imdb Top 250 Movies Csv](web_programming/get_imdb_top_250_movies_csv.py)
 * [Get Imdbtop](web_programming/get_imdbtop.py)
 * [Get Top Billioners](web_programming/get_top_billioners.py)
 * [Get Top Billionaires](web_programming/get_top_billionaires.py)
 * [Get Top Hn Posts](web_programming/get_top_hn_posts.py)
 * [Get User Tweets](web_programming/get_user_tweets.py)
 * [Giphy](web_programming/giphy.py)
Expand Down

116 changes: 66 additions & 50 deletions
machine_learning/local_weighted_learning/local_weighted_learning.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -1,116 +1,128 @@
# Required imports to run this file
import matplotlib.pyplot as plt
import numpy as np


# weighted matrix
def weighted_matrix(point: np.mat, training_data_x: np.mat, bandwidth: float) -> np.mat:
def weighted_matrix(
 point: np.array, training_data_x: np.array, bandwidth: float
) -> np.array:
 """
 Calculate the weight for every point in the
 data set. It takes training_point , query_point, and tau
 Here Tau is not a fixed value it can be varied depends on output.
 tau --> bandwidth
 xmat -->Training data
 point --> the x where we want to make predictions
 >>> weighted_matrix(np.array([1., 1.]),np.mat([[16.99, 10.34], [21.01,23.68],
 ... [24.59,25.69]]), 0.6)
 matrix([[1.43807972e-207, 0.00000000e+000, 0.00000000e+000],
 [0.00000000e+000, 0.00000000e+000, 0.00000000e+000],
 [0.00000000e+000, 0.00000000e+000, 0.00000000e+000]])
 Calculate the weight for every point in the data set.
 point --> the x value at which we want to make predictions
 >>> weighted_matrix(
 ... np.array([1., 1.]),
 ... np.array([[16.99, 10.34], [21.01,23.68], [24.59,25.69]]),
 ... 0.6
 ... )
 array([[1.43807972e-207, 0.00000000e+000, 0.00000000e+000],
 [0.00000000e+000, 0.00000000e+000, 0.00000000e+000],
 [0.00000000e+000, 0.00000000e+000, 0.00000000e+000]])
 """
 # m is the number of training samples
 m, n = np.shape(training_data_x)
 # Initializing weights as identity matrix
 weights = np.mat(np.eye(m))
 m, _ = np.shape(training_data_x) # m is the number of training samples
 weights = np.eye(m) # Initializing weights as identity matrix

 # calculating weights for all training examples [x(i)'s]
 for j in range(m):
 diff = point - training_data_x[j]
 weights[j, j] = np.exp(diff * diff.T / (-2.0 * bandwidth**2))
 weights[j, j] = np.exp(diff @ diff.T / (-2.0 * bandwidth**2))
 return weights


def local_weight(
 point: np.mat, training_data_x: np.mat, training_data_y: np.mat, bandwidth: float
) -> np.mat:
 point: np.array,
 training_data_x: np.array,
 training_data_y: np.array,
 bandwidth: float,
) -> np.array:
 """
 Calculate the local weights using the weight_matrix function on training data.
 Return the weighted matrix.
 >>> local_weight(np.array([1., 1.]),np.mat([[16.99, 10.34], [21.01,23.68],
 ... [24.59,25.69]]),np.mat([[1.01, 1.66, 3.5]]), 0.6)
 matrix([[0.00873174],
 [0.08272556]])
 >>> local_weight(
 ... np.array([1., 1.]),
 ... np.array([[16.99, 10.34], [21.01,23.68], [24.59,25.69]]),
 ... np.array([[1.01, 1.66, 3.5]]),
 ... 0.6
 ... )
 array([[0.00873174],
 [0.08272556]])
 """
 weight = weighted_matrix(point, training_data_x, bandwidth)
 w = (training_data_x.T * (weight * training_data_x)).I * (
 training_data_x.T * weight * training_data_y.T
 w = np.linalg.inv(training_data_x.T @ (weight @ training_data_x)) @ (
 training_data_x.T @ weight @ training_data_y.T
 )

 return w


def local_weight_regression(
 training_data_x: np.mat, training_data_y: np.mat, bandwidth: float
) -> np.mat:
 training_data_x: np.array, training_data_y: np.array, bandwidth: float
) -> np.array:
 """
 Calculate predictions for each data point on axis.
 >>> local_weight_regression(np.mat([[16.99, 10.34], [21.01,23.68],
 ... [24.59,25.69]]),np.mat([[1.01, 1.66, 3.5]]), 0.6)
 Calculate predictions for each data point on axis
 >>> local_weight_regression(
 ... np.array([[16.99, 10.34], [21.01, 23.68], [24.59, 25.69]]),
 ... np.array([[1.01, 1.66, 3.5]]),
 ... 0.6
 ... )
 array([1.07173261, 1.65970737, 3.50160179])
 """
 m, n = np.shape(training_data_x)
 m, _ = np.shape(training_data_x)
 ypred = np.zeros(m)

 for i, item in enumerate(training_data_x):
 ypred[i] = item * local_weight(
 ypred[i] = item @ local_weight(
 item, training_data_x, training_data_y, bandwidth
 )

 return ypred


def load_data(dataset_name: str, cola_name: str, colb_name: str) -> np.mat:
def load_data(
 dataset_name: str, cola_name: str, colb_name: str
) -> tuple[np.array, np.array, np.array, np.array]:
 """
Function used for loading data from the seaborn splitting into x and y points
Load data from seaborn and split it into x and y points
 """
 import seaborn as sns

 data = sns.load_dataset(dataset_name)
 col_a = np.array(data[cola_name]) # total_bill
 col_b = np.array(data[colb_name]) # tip

 mcol_a = np.mat(col_a)
 mcol_b = np.mat(col_b)
 mcol_a = col_a.copy()
 mcol_b = col_b.copy()

 m = np.shape(mcol_b)[1]
 one = np.ones((1, m), dtype=int)
 one = np.ones(np.shape(mcol_b)[0], dtype=int)

 # horizontal stacking
 training_data_x = np.hstack((one.T, mcol_a.T))
 # pairing elements of one and mcol_a
 training_data_x = np.column_stack((one, mcol_a))

 return training_data_x, mcol_b, col_a, col_b


def get_preds(training_data_x: np.mat, mcol_b: np.mat, tau: float) -> np.ndarray:
def get_preds(training_data_x: np.array, mcol_b: np.array, tau: float) -> np.array:
 """
 Get predictions with minimum error for each training data
 >>> get_preds(np.mat([[16.99, 10.34], [21.01,23.68],
 ... [24.59,25.69]]),np.mat([[1.01, 1.66, 3.5]]), 0.6)
 >>> get_preds(
 ... np.array([[16.99, 10.34], [21.01, 23.68], [24.59, 25.69]]),
 ... np.array([[1.01, 1.66, 3.5]]),
 ... 0.6
 ... )
 array([1.07173261, 1.65970737, 3.50160179])
 """
 ypred = local_weight_regression(training_data_x, mcol_b, tau)
 return ypred


def plot_preds(
 training_data_x: np.mat,
 predictions: np.ndarray,
 col_x: np.ndarray,
 col_y: np.ndarray,
 training_data_x: np.array,
 predictions: np.array,
 col_x: np.array,
 col_y: np.array,
 cola_name: str,
 colb_name: str,
) -> plt.plot:
 """
This function used to plot predictions and display the graph
Plot predictions and display the graph
 """
 xsort = training_data_x.copy()
 xsort.sort(axis=0)
Expand All@@ -128,6 +140,10 @@ def plot_preds(


if __name__ == "__main__":
 import doctest

 doctest.testmod()

 training_data_x, mcol_b, col_a, col_b = load_data("tips", "total_bill", "tip")
 predictions = get_preds(training_data_x, mcol_b, 0.5)
 plot_preds(training_data_x, predictions, col_a, col_b, "total_bill", "tip")