Skip to content
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

Assignment 4 #82

Open
wants to merge 3 commits into
base: master
Choose a base branch
from
Open

Assignment 4 #82

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
13e8e17
Assignment 4
skanda99 May 24, 2018
b242963
Assignment 5
skanda99 May 28, 2018
d79b0ac
ML Assignment
skanda99 Jun 24, 2018
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
181 changes: 181 additions & 0 deletions ...on-to-Data-Science/Week-6/Assignment-5/Skanda/.ipynb_checkpoints/MLmodel-checkpoint.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,181 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"' ML Assignment (SVM-linear) (Accuracy: 97.202 %)'"
]
},
"execution_count": 1,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"''' ML Assignment (SVM-linear) (Accuracy: 97.202 %)'''"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"# importing files\n",
"import numpy as np\n",
"import pandas as pd\n",
"import matplotlib.pyplot as plt"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"# getting the dataset\n",
"from sklearn import datasets\n",
"cancer=datasets.load_breast_cancer()\n",
"dataset=pd.DataFrame(cancer['data'],columns=cancer['feature_names'])\n",
"# 0:-malignant,1:-benign\n",
"dataset['Target']=cancer['target']"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
"# features and target\n",
"X=dataset.iloc[:,:-1].values\n",
"y=dataset.iloc[:,30].values"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"# spliting data into test set and train set\n",
"from sklearn.model_selection import train_test_split\n",
"X_train,X_test,y_train,y_test=train_test_split(X,y,test_size=0.25,random_state=0)"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [],
"source": [
"# feature scaling \n",
"from sklearn.preprocessing import StandardScaler\n",
"sc_X=StandardScaler()\n",
"X_train=sc_X.fit_transform(X_train)\n",
"X_test=sc_X.transform(X_test)"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"SVC(C=1.0, cache_size=200, class_weight=None, coef0=0.0,\n",
" decision_function_shape='ovr', degree=3, gamma='auto', kernel='linear',\n",
" max_iter=-1, probability=False, random_state=0, shrinking=True,\n",
" tol=0.001, verbose=False)"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# making SVM-linear classifier\n",
"from sklearn.svm import SVC\n",
"classifier=SVC(kernel='linear',random_state=0)\n",
"classifier.fit(X_train,y_train)"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [],
"source": [
"# predicting test set\n",
"y_pred=classifier.predict(X_test)"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [],
"source": [
"# making of confusion matrix\n",
"from sklearn.metrics import confusion_matrix\n",
"cm=confusion_matrix(y_test,y_pred)"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"array([[51, 2],\n",
" [ 2, 88]], dtype=int64)"
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"cm"
]
},
{
"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": "3.6.4"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
181 changes: 181 additions & 0 deletions Introduction-to-Data-Science/Week-6/Assignment-5/Skanda/MLmodel.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,181 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"' ML Assignment (SVM-linear) (Accuracy: 97.202 %)'"
]
},
"execution_count": 1,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"''' ML Assignment (SVM-linear) (Accuracy: 97.202 %)'''"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"# importing files\n",
"import numpy as np\n",
"import pandas as pd\n",
"import matplotlib.pyplot as plt"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"# getting the dataset\n",
"from sklearn import datasets\n",
"cancer=datasets.load_breast_cancer()\n",
"dataset=pd.DataFrame(cancer['data'],columns=cancer['feature_names'])\n",
"# 0:-malignant,1:-benign\n",
"dataset['Target']=cancer['target']"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
"# features and target\n",
"X=dataset.iloc[:,:-1].values\n",
"y=dataset.iloc[:,30].values"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"# spliting data into test set and train set\n",
"from sklearn.model_selection import train_test_split\n",
"X_train,X_test,y_train,y_test=train_test_split(X,y,test_size=0.25,random_state=0)"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [],
"source": [
"# feature scaling \n",
"from sklearn.preprocessing import StandardScaler\n",
"sc_X=StandardScaler()\n",
"X_train=sc_X.fit_transform(X_train)\n",
"X_test=sc_X.transform(X_test)"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"SVC(C=1.0, cache_size=200, class_weight=None, coef0=0.0,\n",
" decision_function_shape='ovr', degree=3, gamma='auto', kernel='linear',\n",
" max_iter=-1, probability=False, random_state=0, shrinking=True,\n",
" tol=0.001, verbose=False)"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# making SVM-linear classifier\n",
"from sklearn.svm import SVC\n",
"classifier=SVC(kernel='linear',random_state=0)\n",
"classifier.fit(X_train,y_train)"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [],
"source": [
"# predicting test set\n",
"y_pred=classifier.predict(X_test)"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [],
"source": [
"# making of confusion matrix\n",
"from sklearn.metrics import confusion_matrix\n",
"cm=confusion_matrix(y_test,y_pred)"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"array([[51, 2],\n",
" [ 2, 88]], dtype=int64)"
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"cm"
]
},
{
"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": "3.6.4"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
24 changes: 24 additions & 0 deletions Introduction-to-Data-Science/Week-6/Assignment-5/Skanda/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,24 @@
These are the accuracies I got with different models:
1. Logistic Regressor: 95.804 %
2. KNN: 95.104 %
3. SVM (linear): 97.202 %
4. SVM (rbf): 96.503 %
5. Naive Bayes: 91.608 %
6. Decision Tree: 95.804 %
7. Random Forest: 95.804 %


Model Used: SVM (linear) with 97.202 % accuracy


Code flow:
1. Importing files
2. Getting the dataset
3. Making of features and target
4. Splitting of dataset into test and training sets
5. Feature scaling (Important for SVM linear)
6. Making of SVM classifier with linear kernel
7. Predicting test set
8. Making of confusion matrix


4 changes: 4 additions & 0 deletions Introduction-to-Data-Science/Week-6/Assignment-5/Skanda/desktop.ini
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,4 @@
[ViewState]
Mode=
Vid=
FolderType=Documents
Loading