Skip to content

Commit

Permalink
Add files via upload
Browse files Browse the repository at this point in the history
  • Loading branch information
TStud authored Nov 6, 2019
1 parent 3de5ccd commit 86f5996
Show file tree
Hide file tree
Showing 2 changed files with 417 additions and 0 deletions.
238 changes: 238 additions & 0 deletions EDA (Wine Dataset).ipynb
Original file line number Diff line number Diff line change
@@ -0,0 +1,238 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"import numpy as np\n",
"import pandas as pd\n",
"import matplotlib.pyplot as plt\n",
"import seaborn as sns\n",
"%matplotlib inline\n",
"\n",
"from sklearn.preprocessing import StandardScaler\n",
"from sklearn.model_selection import train_test_split\n",
"from sklearn.model_selection import cross_val_score\n",
"\n",
"# KNN classifier\n",
"from sklearn.neighbors import KNeighborsClassifier\n",
"\n",
"# Evaluation Metrics\n",
"from sklearn.metrics import accuracy_score\n",
"from sklearn.metrics import confusion_matrix"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"#Import scikit-learn dataset library\n",
"from sklearn import datasets\n",
"\n",
"#Load dataset\n",
"wine = datasets.load_wine()"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"['alcohol', 'malic_acid', 'ash', 'alcalinity_of_ash', 'magnesium', 'total_phenols', 'flavanoids', 'nonflavanoid_phenols', 'proanthocyanins', 'color_intensity', 'hue', 'od280/od315_of_diluted_wines', 'proline']\n"
]
}
],
"source": [
"print(wine.feature_names)"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"['class_0' 'class_1' 'class_2']\n"
]
}
],
"source": [
"print(wine.target_names)"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"(178, 13)\n"
]
}
],
"source": [
"print(wine.data.shape)"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [],
"source": [
"# Spliting of the dataset into training set and test set\n",
"X_train, X_test, y_train, y_test = train_test_split(wine.data, wine.target, test_size=0.3) # 70% training and 30% test"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [],
"source": [
"#Create KNN Classifier\n",
"knn = KNeighborsClassifier(n_neighbors=5)\n",
"\n",
"#Train the model using the training sets\n",
"knn.fit(X_train, y_train)\n",
"\n",
"#Predict the response for test dataset\n",
"y_pred = knn.predict(X_test)"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Accuracy: 0.5925925925925926\n"
]
}
],
"source": [
"#Import scikit-learn metrics module for accuracy calculation\n",
"from sklearn import metrics\n",
"# Model Accuracy, how often is the classifier correct?\n",
"print(\"Accuracy:\",metrics.accuracy_score(y_test, y_pred))"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [],
"source": [
"#Create KNN Classifier\n",
"knn = KNeighborsClassifier(n_neighbors=7)\n",
"\n",
"#Train the model using the training sets\n",
"knn.fit(X_train, y_train)\n",
"\n",
"#Predict the response for test dataset\n",
"y_pred = knn.predict(X_test)"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Accuracy: 0.6296296296296297\n"
]
}
],
"source": [
"#Import scikit-learn metrics module for accuracy calculation\n",
"from sklearn import metrics\n",
"# Model Accuracy, how often is the classifier correct?\n",
"print(\"Accuracy:\",metrics.accuracy_score(y_test, y_pred))"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {},
"outputs": [],
"source": [
"#Create KNN Classifier\n",
"knn = KNeighborsClassifier(n_neighbors=8)\n",
"\n",
"#Train the model using the training sets\n",
"knn.fit(X_train, y_train)\n",
"\n",
"#Predict the response for test dataset\n",
"y_pred = knn.predict(X_test)"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Accuracy: 0.6111111111111112\n"
]
}
],
"source": [
"#scikit-learn metrics module for accuracy calculation\n",
"from sklearn import metrics\n",
"# Model Accuracy, how often is the classifier correct?\n",
"print(\"Accuracy:\",metrics.accuracy_score(y_test, y_pred))"
]
},
{
"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": "3.6.5"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
Loading

0 comments on commit 86f5996

Please sign in to comment.