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

Jump to bottom

Update Chapter 4.ipynb #27

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

Update Chapter 4.ipynb #27

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
32 changes: 14 additions & 18 deletions Notebooks/Chapter 4.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -178,11 +178,11 @@
"df_no = df[df.default2 == 0].sample(frac=0.15)\n",
"# Take all samples where target value is 'yes'\n",
"df_yes = df[df.default2 == 1]\n",
"df_ = df_no.append(df_yes)\n",
"df_ = df.concat([df_yes, df_no])\n",
"\n",
"ax1.scatter(df_[df_.default == 'Yes'].balance, df_[df_.default == 'Yes'].income, s=40, c='orange', marker='+',\n",
" linewidths=1)\n",
"ax1.scatter(df_[df_.default == 'No'].balance, df_[df_.default == 'No'].income, s=40, marker='o', linewidths='1',\n",
"ax1.scatter(df_[df_.default == 'No'].balance, df_[df_.default == 'No'].income, s=40, marker='o', linewidths=1,\n",
" edgecolors='lightblue', facecolors='white', alpha=.6)\n",
"\n",
"ax1.set_ylim(ymin=0)\n",
Expand Down Expand Up @@ -228,7 +228,7 @@
"# and predicted classification.\n",
"X_test = np.arange(df.balance.min(), df.balance.max()).reshape(-1,1)\n",
"\n",
"clf = skl_lm.LogisticRegression(solver='newton-cg')\n",
"clf = skl_lm.LogisticRegression(solver='lbfgs')\n",
"clf.fit(X_train,y)\n",
"prob = clf.predict_proba(X_test)\n",
"\n",
Expand Down Expand Up @@ -297,7 +297,7 @@
"source": [
"# Using newton-cg solver, the coefficients are equal/closest to the ones in the book. \n",
"# I do not know the details on the differences between the solvers.\n",
"clf = skl_lm.LogisticRegression(solver='newton-cg')\n",
"clf = skl_lm.LogisticRegression(solver='lbfgs')\n",
"X_train = df.balance.values.reshape(-1,1)\n",
"clf.fit(X_train,y)\n",
"print(clf)\n",
Expand Down Expand Up @@ -391,8 +391,7 @@
}
],
"source": [
"X_train = sm.add_constant(df.balance)\n",
"est = smf.Logit(y.ravel(), X_train).fit()\n",
"est = smf.logit(formula='default2 ~ 1 + balance', data=df).fit()\n",
"est.summary2().tables[1]"
]
},
Expand Down Expand Up @@ -481,10 +480,8 @@
}
],
"source": [
"X_train = sm.add_constant(df.student2)\n",
"y = df.default2\n",
"\n",
"est = smf.Logit(y, X_train).fit()\n",
"est = smf.logit(formula='default2 ~ 1 + student2', data=df).fit()\n",
"est.summary2().tables[1]"
]
},
Expand Down Expand Up @@ -593,8 +590,7 @@
}
],
"source": [
"X_train = sm.add_constant(df[['balance', 'income', 'student2']])\n",
"est = smf.Logit(y, X_train).fit()\n",
"est = smf.logit(formula='default2 ~ 1 + student2', data=df).fit()\n",
"est.summary2().tables[1]"
]
},
Expand Down Expand Up @@ -622,8 +618,8 @@
"# Vector with balance values for plotting\n",
"X_test = np.arange(df.balance.min(), df.balance.max()).reshape(-1,1)\n",
"\n",
"clf = skl_lm.LogisticRegression(solver='newton-cg')\n",
"clf2 = skl_lm.LogisticRegression(solver='newton-cg')\n",
"clf = skl_lm.LogisticRegression(solver='lbfgs')\n",
"clf2 = skl_lm.LogisticRegression(solver='lbfgs')\n",
"\n",
"clf.fit(X_train,y)\n",
"clf2.fit(X_train2,y2)\n",
Expand Down Expand Up @@ -734,7 +730,7 @@
"ax1.legend(loc=2)\n",
"\n",
"# Right plot\n",
"sns.boxplot('student', 'balance', data=df, orient='v', ax=ax2, palette=c_palette);"
"sns.boxplot(x='student', y='balance', data=df, orient='v', ax=ax2, palette=c_palette);"
]
},
{
Expand Down Expand Up @@ -808,8 +804,8 @@
}
],
"source": [
"X = df[['balance', 'income', 'student2']].as_matrix()\n",
"y = df.default2.as_matrix()\n",
"X = df[['balance', 'income', 'student2']].values\n",
"y = df.default2.values\n",
"\n",
"lda = LinearDiscriminantAnalysis(solver='svd')\n",
"y_pred = lda.fit(X, y).predict(X)\n",
Expand Down Expand Up @@ -1310,8 +1306,8 @@
"X_test = X_scaled[:1000,:]\n",
"y_test = y[:1000]\n",
"\n",
"def KNN(n_neighbors=1, weights='uniform'):\n",
" clf = neighbors.KNeighborsClassifier(n_neighbors, weights)\n",
"def KNN(n_neighbors=1,):\n",
" clf = neighbors.KNeighborsClassifier(n_neighbors, weights = 'uniform')\n",
" clf.fit(X_train, y_train)\n",
" pred = clf.predict(X_test)\n",
" score = clf.score(X_test, y_test)\n",
Expand Down