Skip to content

Logistics Regression from scratch #12

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

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Logistics Regression from scratch #12

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
276 changes: 276 additions & 0 deletions Untitled.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,276 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [],
"source": [
"import numpy as np\n",
"from sklearn.datasets import load_breast_cancer"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {},
"outputs": [],
"source": [
"data = load_breast_cancer()"
]
},
{
"cell_type": "code",
"execution_count": 36,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"array([0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1,\n",
" 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0,\n",
" 0, 0, 1, 0, 1, 1, 1, 1, 1, 0, 0, 1, 0, 0, 1, 1, 1, 1, 0, 1, 0, 0,\n",
" 1, 1, 1, 1, 0, 1, 0, 0, 1, 0, 1, 0, 0, 1, 1, 1, 0, 0, 1, 0, 0, 0,\n",
" 1, 1, 1, 0, 1, 1, 0, 0, 1, 1, 1, 0, 0, 1, 1, 1, 1, 0, 1, 1, 0, 1,\n",
" 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 1, 0, 0, 1, 1, 1, 0, 0, 1, 0, 1, 0,\n",
" 0, 1, 0, 0, 1, 1, 0, 1, 1, 0, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1,\n",
" 1, 1, 0, 1, 1, 1, 1, 0, 0, 1, 0, 1, 1, 0, 0, 1, 1, 0, 0, 1, 1, 1,\n",
" 1, 0, 1, 1, 0, 0, 0, 1, 0, 1, 0, 1, 1, 1, 0, 1, 1, 0, 0, 1, 0, 0,\n",
" 0, 0, 1, 0, 0, 0, 1, 0, 1, 0, 1, 1, 0, 1, 0, 0, 0, 0, 1, 1, 0, 0,\n",
" 1, 1, 1, 0, 1, 1, 1, 1, 1, 0, 0, 1, 1, 0, 1, 1, 0, 0, 1, 0, 1, 1,\n",
" 1, 1, 0, 1, 1, 1, 1, 1, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
" 0, 0, 1, 1, 1, 1, 1, 1, 0, 1, 0, 1, 1, 0, 1, 1, 0, 1, 0, 0, 1, 1,\n",
" 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 0, 1, 0, 1, 1, 1, 1, 1,\n",
" 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 0, 1, 0, 1, 1, 1, 1, 0, 0,\n",
" 0, 1, 1, 1, 1, 0, 1, 0, 1, 0, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 0,\n",
" 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 1, 0, 0, 0, 1, 0, 0,\n",
" 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 0, 1, 1, 1, 0, 1, 1, 0, 0, 1, 1,\n",
" 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 0, 1, 1, 0,\n",
" 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 0, 0, 1, 0, 1, 1, 1, 1,\n",
" 1, 0, 1, 1, 0, 1, 0, 1, 1, 0, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0,\n",
" 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1,\n",
" 1, 1, 1, 0, 1, 0, 1, 1, 0, 1, 1, 1, 1, 1, 0, 0, 1, 0, 1, 0, 1, 1,\n",
" 1, 1, 1, 0, 1, 1, 0, 1, 0, 1, 0, 0, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1,\n",
" 1, 1, 1, 1, 1, 0, 1, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n",
" 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 1])"
]
},
"execution_count": 36,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"X = data.data\n",
"y = data.target\n",
"y"
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {},
"outputs": [],
"source": [
"# the logistic function or sigmod function\n",
"def sigmod(X,w):\n",
" z = np.dot(X,w)\n",
" return 1 / (1 + np.exp(-z))"
]
},
{
"cell_type": "code",
"execution_count": 18,
"metadata": {},
"outputs": [],
"source": [
"# calculate for the loss \n",
"\n",
"def loss(h,y):\n",
" return (-y * np.log(h) - (1 - y) * np.log(1 - h)).mean()"
]
},
{
"cell_type": "code",
"execution_count": 20,
"metadata": {},
"outputs": [],
"source": [
"def SGD(X, h, y):\n",
" return np.dot(X.T, (h - y)) / y.shape[0]\n",
"def update_w_l(w, l_rate, gradient):\n",
" return w - l_rate * gradient"
]
},
{
"cell_type": "code",
"execution_count": 26,
"metadata": {},
"outputs": [],
"source": [
"num_iter = 100000\n",
"\n",
"intercept = np.ones((X.shape[0], 1)) \n",
"X = np.concatenate((intercept, X), axis=1)\n",
"theta = np.zeros(X.shape[1])\n",
"\n",
"for i in range(num_iter):\n",
" h = sigmod(X, theta)\n",
" gradient = SGD(X, h, y)\n",
" theta = update_w_l(theta, 0.1, gradient)\n"
]
},
{
"cell_type": "code",
"execution_count": 27,
"metadata": {},
"outputs": [],
"source": [
"result = sigmod(X, theta)"
]
},
{
"cell_type": "code",
"execution_count": 31,
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"result = pd.DataFrame(result)"
]
},
{
"cell_type": "code",
"execution_count": 34,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>0</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>564</th>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>565</th>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>566</th>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>567</th>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>568</th>\n",
" <td>1.0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>569 rows × 1 columns</p>\n",
"</div>"
],
"text/plain": [
" 0\n",
"0 1.0\n",
"1 1.0\n",
"2 1.0\n",
"3 1.0\n",
"4 1.0\n",
".. ...\n",
"564 1.0\n",
"565 1.0\n",
"566 1.0\n",
"567 1.0\n",
"568 1.0\n",
"\n",
"[569 rows x 1 columns]"
]
},
"execution_count": 34,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"result"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.7.6"
}
},
"nbformat": 4,
"nbformat_minor": 4
}
52 changes: 52 additions & 0 deletions exchange.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,52 @@
import numpy as np
from sklearn.datasets import load_breast_cancer
data = load_breast_cancer()

X = data.data[:, :2]
y = (data.target != 0) * 1
class LogisticRegression:
def __init__(self, lr=0.01, num_iter=10, fit_intercept=True):
self.lr = lr
self.num_iter = num_iter
self.fit_intercept = fit_intercept

def intercepts(self, X):
intercept = np.ones((X.shape[0], 1))
return np.concatenate((intercept, X), axis=1)

def sigmoid(self, z):
return 1 / (1 + np.exp(-z))
def loss(self, h, y):
return (-y * np.log(h) - (1 - y) * np.log(1 - h)).mean()

def fit(self, X, y):
if self.fit_intercept:
X = self.intercepts(X)

# weights initialization
self.theta = np.zeros(X.shape[1])

for i in range(self.num_iter):
z = np.dot(X, self.theta)
h = self.sigmoid(z)
gradient = np.dot(X.T, (h - y)) / y.size
self.theta -= self.lr * gradient

if(i % 100 == 0):
z = np.dot(X, self.theta)
h = self.sigmoid(z)
print(f'loss: {self.loss(h, y)} \t')

def predict_prob(self, X):
if self.fit_intercept:
X = self.intercepts(X)

return self.sigmoid(np.dot(X, self.theta))

def predict(self, X, threshold):
return self.predict_prob(X) >= threshold
model = LogisticRegression(lr=0.1, num_iter=30000)
model.fit(X, y)
preds = model.predict(X, threshold=10)
# accuracy
accuracy = print(preds)