Chapter 50
workshop uv fastapi
NotebookPython 3 (ipykernel)24 cells
This is a starter notebook for an updated module 5 of ML Zoomcamp
The code is based on the modules 3 and 4. We use the same dataset: telco customer churn
In [2]python · cell 2
python
import pandas as pd
import numpy as np
import sklearnIn [3]python · cell 3
python
print(f'pandas=={pd.__version__}')
print(f'numpy=={np.__version__}')
print(f'sklearn=={sklearn.__version__}')Output
pandas==2.3.1 numpy==2.3.1 sklearn==1.7.0
In [4]python · cell 4
python
from sklearn.feature_extraction import DictVectorizer
from sklearn.linear_model import LogisticRegressionIn [5]python · cell 5
python
data_url = 'https://raw.githubusercontent.com/alexeygrigorev/mlbookcamp-code/master/chapter-03-churn-prediction/WA_Fn-UseC_-Telco-Customer-Churn.csv'
df = pd.read_csv(data_url)
df.columns = df.columns.str.lower().str.replace(' ', '_')
categorical_columns = list(df.dtypes[df.dtypes == 'object'].index)
for c in categorical_columns:
df[c] = df[c].str.lower().str.replace(' ', '_')
df.totalcharges = pd.to_numeric(df.totalcharges, errors='coerce')
df.totalcharges = df.totalcharges.fillna(0)
df.churn = (df.churn == 'yes').astype(int)In [6]python · cell 6
python
y_train = df.churnIn [7]python · cell 7
python
numerical = ['tenure', 'monthlycharges', 'totalcharges']
categorical = [
'gender',
'seniorcitizen',
'partner',
'dependents',
'phoneservice',
'multiplelines',
'internetservice',
'onlinesecurity',
'onlinebackup',
'deviceprotection',
'techsupport',
'streamingtv',
'streamingmovies',
'contract',
'paperlessbilling',
'paymentmethod',
]In [8]python · cell 8
python
dv = DictVectorizer()
train_dict = df[categorical + numerical].to_dict(orient='records')
X_train = dv.fit_transform(train_dict)
model = LogisticRegression(solver='liblinear')
model.fit(X_train, y_train)Output
LogisticRegression(solver='liblinear')
#sk-container-id-1 {
/* Definition of color scheme common for light and dark mode */
--sklearn-color-text: #000;
--sklearn-color-text-muted: #666;
--sklearn-color-line: gray;
/* Definition of color scheme for unfitted estimators */
--sklearn-color-unfitted-level-0: #fff5e6;
--sklearn-color-unfitted-level-1: #f6e4d2;
--sklearn-color-unfitted-level-2: #ffe0b3;
--sklearn-color-unfitted-level-3: chocolate;
/* Definition of color scheme for fitted estimators */
--sklearn-color-fitted-level-0: #f0f8ff;
--sklearn-color-fitted-level-1: #d4ebff;
--sklearn-color-fitted-level-2: #b3dbfd;
--sklearn-color-fitted-level-3: cornflowerblue;
/* Specific color for light theme */
--sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));
--sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));
--sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));
--sklearn-color-icon: #696969;
@media (prefers-color-scheme: dark) {
/* Redefinition of color scheme for dark theme */
--sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));
--sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));
--sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));
--sklearn-color-icon: #878787;
}
}
#sk-container-id-1 {
color: var(--sklearn-color-text);
}
#sk-container-id-1 pre {
padding: 0;
}
#sk-container-id-1 input.sk-hidden--visually {
border: 0;
clip: rect(1px 1px 1px 1px);
clip: rect(1px, 1px, 1px, 1px);
height: 1px;
margin: -1px;
overflow: hidden;
padding: 0;
position: absolute;
width: 1px;
}
#sk-container-id-1 div.sk-dashed-wrapped {
border: 1px dashed var(--sklearn-color-line);
margin: 0 0.4em 0.5em 0.4em;
box-sizing: border-box;
padding-bottom: 0.4em;
background-color: var(--sklearn-color-background);
}
#sk-container-id-1 div.sk-container {
/* jupyter's `normalize.less` sets `[hidden] { display: none; }`
but bootstrap.min.css set `[hidden] { display: none !important; }`
so we also need the `!important` here to be able to override the
default hidden behavior on the sphinx rendered scikit-learn.org.
See: https://github.com/scikit-learn/scikit-learn/issues/21755 */
display: inline-block !important;
position: relative;
}
#sk-container-id-1 div.sk-text-repr-fallback {
display: none;
}
div.sk-parallel-item,
div.sk-serial,
div.sk-item {
/* draw centered vertical line to link estimators */
background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));
background-size: 2px 100%;
background-repeat: no-repeat;
background-position: center center;
}
/* Parallel-specific style estimator block */
#sk-container-id-1 div.sk-parallel-item::after {
content: "";
width: 100%;
border-bottom: 2px solid var(--sklearn-color-text-on-default-background);
flex-grow: 1;
}
#sk-container-id-1 div.sk-parallel {
display: flex;
align-items: stretch;
justify-content: center;
background-color: var(--sklearn-color-background);
position: relative;
}
#sk-container-id-1 div.sk-parallel-item {
display: flex;
flex-direction: column;
}
#sk-container-id-1 div.sk-parallel-item:first-child::after {
align-self: flex-end;
width: 50%;
}
#sk-container-id-1 div.sk-parallel-item:last-child::after {
align-self: flex-start;
width: 50%;
}
#sk-container-id-1 div.sk-parallel-item:only-child::after {
width: 0;
}
/* Serial-specific style estimator block */
#sk-container-id-1 div.sk-serial {
display: flex;
flex-direction: column;
align-items: center;
background-color: var(--sklearn-color-background);
padding-right: 1em;
padding-left: 1em;
}
/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is
clickable and can be expanded/collapsed.
- Pipeline and ColumnTransformer use this feature and define the default style
- Estimators will overwrite some part of the style using the `sk-estimator` class
*/
/* Pipeline and ColumnTransformer style (default) */
#sk-container-id-1 div.sk-toggleable {
/* Default theme specific background. It is overwritten whether we have a
specific estimator or a Pipeline/ColumnTransformer */
background-color: var(--sklearn-color-background);
}
/* Toggleable label */
#sk-container-id-1 label.sk-toggleable__label {
cursor: pointer;
display: flex;
width: 100%;
margin-bottom: 0;
padding: 0.5em;
box-sizing: border-box;
text-align: center;
align-items: start;
justify-content: space-between;
gap: 0.5em;
}
#sk-container-id-1 label.sk-toggleable__label .caption {
font-size: 0.6rem;
font-weight: lighter;
color: var(--sklearn-color-text-muted);
}
#sk-container-id-1 label.sk-toggleable__label-arrow:before {
/* Arrow on the left of the label */
content: "▸";
float: left;
margin-right: 0.25em;
color: var(--sklearn-color-icon);
}
#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {
color: var(--sklearn-color-text);
}
/* Toggleable content - dropdown */
#sk-container-id-1 div.sk-toggleable__content {
display: none;
text-align: left;
/* unfitted */
background-color: var(--sklearn-color-unfitted-level-0);
}
#sk-container-id-1 div.sk-toggleable__content.fitted {
/* fitted */
background-color: var(--sklearn-color-fitted-level-0);
}
#sk-container-id-1 div.sk-toggleable__content pre {
margin: 0.2em;
border-radius: 0.25em;
color: var(--sklearn-color-text);
/* unfitted */
background-color: var(--sklearn-color-unfitted-level-0);
}
#sk-container-id-1 div.sk-toggleable__content.fitted pre {
/* unfitted */
background-color: var(--sklearn-color-fitted-level-0);
}
#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {
/* Expand drop-down */
display: block;
width: 100%;
overflow: visible;
}
#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {
content: "▾";
}
/* Pipeline/ColumnTransformer-specific style */
#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {
color: var(--sklearn-color-text);
background-color: var(--sklearn-color-unfitted-level-2);
}
#sk-container-id-1 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {
background-color: var(--sklearn-color-fitted-level-2);
}
/* Estimator-specific style */
/* Colorize estimator box */
#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {
/* unfitted */
background-color: var(--sklearn-color-unfitted-level-2);
}
#sk-container-id-1 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {
/* fitted */
background-color: var(--sklearn-color-fitted-level-2);
}
#sk-container-id-1 div.sk-label label.sk-toggleable__label,
#sk-container-id-1 div.sk-label label {
/* The background is the default theme color */
color: var(--sklearn-color-text-on-default-background);
}
/* On hover, darken the color of the background */
#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {
color: var(--sklearn-color-text);
background-color: var(--sklearn-color-unfitted-level-2);
}
/* Label box, darken color on hover, fitted */
#sk-container-id-1 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {
color: var(--sklearn-color-text);
background-color: var(--sklearn-color-fitted-level-2);
}
/* Estimator label */
#sk-container-id-1 div.sk-label label {
font-family: monospace;
font-weight: bold;
display: inline-block;
line-height: 1.2em;
}
#sk-container-id-1 div.sk-label-container {
text-align: center;
}
/* Estimator-specific */
#sk-container-id-1 div.sk-estimator {
font-family: monospace;
border: 1px dotted var(--sklearn-color-border-box);
border-radius: 0.25em;
box-sizing: border-box;
margin-bottom: 0.5em;
/* unfitted */
background-color: var(--sklearn-color-unfitted-level-0);
}
#sk-container-id-1 div.sk-estimator.fitted {
/* fitted */
background-color: var(--sklearn-color-fitted-level-0);
}
/* on hover */
#sk-container-id-1 div.sk-estimator:hover {
/* unfitted */
background-color: var(--sklearn-color-unfitted-level-2);
}
#sk-container-id-1 div.sk-estimator.fitted:hover {
/* fitted */
background-color: var(--sklearn-color-fitted-level-2);
}
/* Specification for estimator info (e.g. "i" and "?") */
/* Common style for "i" and "?" */
.sk-estimator-doc-link,
a:link.sk-estimator-doc-link,
a:visited.sk-estimator-doc-link {
float: right;
font-size: smaller;
line-height: 1em;
font-family: monospace;
background-color: var(--sklearn-color-background);
border-radius: 1em;
height: 1em;
width: 1em;
text-decoration: none !important;
margin-left: 0.5em;
text-align: center;
/* unfitted */
border: var(--sklearn-color-unfitted-level-1) 1pt solid;
color: var(--sklearn-color-unfitted-level-1);
}
.sk-estimator-doc-link.fitted,
a:link.sk-estimator-doc-link.fitted,
a:visited.sk-estimator-doc-link.fitted {
/* fitted */
border: var(--sklearn-color-fitted-level-1) 1pt solid;
color: var(--sklearn-color-fitted-level-1);
}
/* On hover */
div.sk-estimator:hover .sk-estimator-doc-link:hover,
.sk-estimator-doc-link:hover,
div.sk-label-container:hover .sk-estimator-doc-link:hover,
.sk-estimator-doc-link:hover {
/* unfitted */
background-color: var(--sklearn-color-unfitted-level-3);
color: var(--sklearn-color-background);
text-decoration: none;
}
div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,
.sk-estimator-doc-link.fitted:hover,
div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,
.sk-estimator-doc-link.fitted:hover {
/* fitted */
background-color: var(--sklearn-color-fitted-level-3);
color: var(--sklearn-color-background);
text-decoration: none;
}
/* Span, style for the box shown on hovering the info icon */
.sk-estimator-doc-link span {
display: none;
z-index: 9999;
position: relative;
font-weight: normal;
right: .2ex;
padding: .5ex;
margin: .5ex;
width: min-content;
min-width: 20ex;
max-width: 50ex;
color: var(--sklearn-color-text);
box-shadow: 2pt 2pt 4pt #999;
/* unfitted */
background: var(--sklearn-color-unfitted-level-0);
border: .5pt solid var(--sklearn-color-unfitted-level-3);
}
.sk-estimator-doc-link.fitted span {
/* fitted */
background: var(--sklearn-color-fitted-level-0);
border: var(--sklearn-color-fitted-level-3);
}
.sk-estimator-doc-link:hover span {
display: block;
}
/* "?"-specific style due to the `<a>` HTML tag */
#sk-container-id-1 a.estimator_doc_link {
float: right;
font-size: 1rem;
line-height: 1em;
font-family: monospace;
background-color: var(--sklearn-color-background);
border-radius: 1rem;
height: 1rem;
width: 1rem;
text-decoration: none;
/* unfitted */
color: var(--sklearn-color-unfitted-level-1);
border: var(--sklearn-color-unfitted-level-1) 1pt solid;
}
#sk-container-id-1 a.estimator_doc_link.fitted {
/* fitted */
border: var(--sklearn-color-fitted-level-1) 1pt solid;
color: var(--sklearn-color-fitted-level-1);
}
/* On hover */
#sk-container-id-1 a.estimator_doc_link:hover {
/* unfitted */
background-color: var(--sklearn-color-unfitted-level-3);
color: var(--sklearn-color-background);
text-decoration: none;
}
#sk-container-id-1 a.estimator_doc_link.fitted:hover {
/* fitted */
background-color: var(--sklearn-color-fitted-level-3);
}
.estimator-table summary {
padding: .5rem;
font-family: monospace;
cursor: pointer;
}
.estimator-table details[open] {
padding-left: 0.1rem;
padding-right: 0.1rem;
padding-bottom: 0.3rem;
}
.estimator-table .parameters-table {
margin-left: auto !important;
margin-right: auto !important;
}
.estimator-table .parameters-table tr:nth-child(odd) {
background-color: #fff;
}
.estimator-table .parameters-table tr:nth-child(even) {
background-color: #f6f6f6;
}
.estimator-table .parameters-table tr:hover {
background-color: #e0e0e0;
}
.estimator-table table td {
border: 1px solid rgba(106, 105, 104, 0.232);
}
.user-set td {
color:rgb(255, 94, 0);
text-align: left;
}
.user-set td.value pre {
color:rgb(255, 94, 0) !important;
background-color: transparent !important;
}
.default td {
color: black;
text-align: left;
}
.user-set td i,
.default td i {
color: black;
}
.copy-paste-icon {
background-image: url(data:image/svg+xml;base64,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);
background-repeat: no-repeat;
background-size: 14px 14px;
background-position: 0;
display: inline-block;
width: 14px;
height: 14px;
cursor: pointer;
}
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
LogisticRegression(solver='liblinear')In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
LogisticRegression
Parameters
| penalty | 'l2' | |
| dual | False | |
| tol | 0.0001 | |
| C | 1.0 | |
| fit_intercept | True | |
| intercept_scaling | 1 | |
| class_weight | None | |
| random_state | None | |
| solver | 'liblinear' | |
| max_iter | 100 | |
| multi_class | 'deprecated' | |
| verbose | 0 | |
| warm_start | False | |
| n_jobs | None | |
| l1_ratio | None |
In [11]python · cell 9
python
datapoint = {
'gender': 'female',
'seniorcitizen': 0,
'partner': 'yes',
'dependents': 'no',
'phoneservice': 'no',
'multiplelines': 'no_phone_service',
'internetservice': 'dsl',
'onlinesecurity': 'no',
'onlinebackup': 'yes',
'deviceprotection': 'no',
'techsupport': 'no',
'streamingtv': 'no',
'streamingmovies': 'no',
'contract': 'month-to-month',
'paperlessbilling': 'yes',
'paymentmethod': 'electronic_check',
'tenure': 1,
'monthlycharges': 29.85,
'totalcharges': 29.85
}In [14]python · cell 10
python
X = dv.transform(datapoint)In [ ]python · cell 11
python
model.predict_proba(X)[0, 1]Output
np.float64(0.33617994559536546)
In [20]python · cell 12
python
import pickleIn [21]python · cell 13
python
with open('model.bin', 'wb') as f_out:
pickle.dump((dv, model), f_out)In [22]python · cell 14
python
with open('model.bin', 'rb') as f_in:
(dv, model) = pickle.load(f_in)In [25]python · cell 15
python
from sklearn.pipeline import make_pipelineIn [26]python · cell 16
python
pipeline = make_pipeline(
DictVectorizer(),
LogisticRegression(solver='liblinear')
)In [29]python · cell 17
python
pipeline.fit(train_dict, y_train)Output
Pipeline(steps=[('dictvectorizer', DictVectorizer()),
('logisticregression', LogisticRegression(solver='liblinear'))])#sk-container-id-4 {
/* Definition of color scheme common for light and dark mode */
--sklearn-color-text: #000;
--sklearn-color-text-muted: #666;
--sklearn-color-line: gray;
/* Definition of color scheme for unfitted estimators */
--sklearn-color-unfitted-level-0: #fff5e6;
--sklearn-color-unfitted-level-1: #f6e4d2;
--sklearn-color-unfitted-level-2: #ffe0b3;
--sklearn-color-unfitted-level-3: chocolate;
/* Definition of color scheme for fitted estimators */
--sklearn-color-fitted-level-0: #f0f8ff;
--sklearn-color-fitted-level-1: #d4ebff;
--sklearn-color-fitted-level-2: #b3dbfd;
--sklearn-color-fitted-level-3: cornflowerblue;
/* Specific color for light theme */
--sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));
--sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));
--sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));
--sklearn-color-icon: #696969;
@media (prefers-color-scheme: dark) {
/* Redefinition of color scheme for dark theme */
--sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));
--sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));
--sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));
--sklearn-color-icon: #878787;
}
}
#sk-container-id-4 {
color: var(--sklearn-color-text);
}
#sk-container-id-4 pre {
padding: 0;
}
#sk-container-id-4 input.sk-hidden--visually {
border: 0;
clip: rect(1px 1px 1px 1px);
clip: rect(1px, 1px, 1px, 1px);
height: 1px;
margin: -1px;
overflow: hidden;
padding: 0;
position: absolute;
width: 1px;
}
#sk-container-id-4 div.sk-dashed-wrapped {
border: 1px dashed var(--sklearn-color-line);
margin: 0 0.4em 0.5em 0.4em;
box-sizing: border-box;
padding-bottom: 0.4em;
background-color: var(--sklearn-color-background);
}
#sk-container-id-4 div.sk-container {
/* jupyter's `normalize.less` sets `[hidden] { display: none; }`
but bootstrap.min.css set `[hidden] { display: none !important; }`
so we also need the `!important` here to be able to override the
default hidden behavior on the sphinx rendered scikit-learn.org.
See: https://github.com/scikit-learn/scikit-learn/issues/21755 */
display: inline-block !important;
position: relative;
}
#sk-container-id-4 div.sk-text-repr-fallback {
display: none;
}
div.sk-parallel-item,
div.sk-serial,
div.sk-item {
/* draw centered vertical line to link estimators */
background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));
background-size: 2px 100%;
background-repeat: no-repeat;
background-position: center center;
}
/* Parallel-specific style estimator block */
#sk-container-id-4 div.sk-parallel-item::after {
content: "";
width: 100%;
border-bottom: 2px solid var(--sklearn-color-text-on-default-background);
flex-grow: 1;
}
#sk-container-id-4 div.sk-parallel {
display: flex;
align-items: stretch;
justify-content: center;
background-color: var(--sklearn-color-background);
position: relative;
}
#sk-container-id-4 div.sk-parallel-item {
display: flex;
flex-direction: column;
}
#sk-container-id-4 div.sk-parallel-item:first-child::after {
align-self: flex-end;
width: 50%;
}
#sk-container-id-4 div.sk-parallel-item:last-child::after {
align-self: flex-start;
width: 50%;
}
#sk-container-id-4 div.sk-parallel-item:only-child::after {
width: 0;
}
/* Serial-specific style estimator block */
#sk-container-id-4 div.sk-serial {
display: flex;
flex-direction: column;
align-items: center;
background-color: var(--sklearn-color-background);
padding-right: 1em;
padding-left: 1em;
}
/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is
clickable and can be expanded/collapsed.
- Pipeline and ColumnTransformer use this feature and define the default style
- Estimators will overwrite some part of the style using the `sk-estimator` class
*/
/* Pipeline and ColumnTransformer style (default) */
#sk-container-id-4 div.sk-toggleable {
/* Default theme specific background. It is overwritten whether we have a
specific estimator or a Pipeline/ColumnTransformer */
background-color: var(--sklearn-color-background);
}
/* Toggleable label */
#sk-container-id-4 label.sk-toggleable__label {
cursor: pointer;
display: flex;
width: 100%;
margin-bottom: 0;
padding: 0.5em;
box-sizing: border-box;
text-align: center;
align-items: start;
justify-content: space-between;
gap: 0.5em;
}
#sk-container-id-4 label.sk-toggleable__label .caption {
font-size: 0.6rem;
font-weight: lighter;
color: var(--sklearn-color-text-muted);
}
#sk-container-id-4 label.sk-toggleable__label-arrow:before {
/* Arrow on the left of the label */
content: "▸";
float: left;
margin-right: 0.25em;
color: var(--sklearn-color-icon);
}
#sk-container-id-4 label.sk-toggleable__label-arrow:hover:before {
color: var(--sklearn-color-text);
}
/* Toggleable content - dropdown */
#sk-container-id-4 div.sk-toggleable__content {
display: none;
text-align: left;
/* unfitted */
background-color: var(--sklearn-color-unfitted-level-0);
}
#sk-container-id-4 div.sk-toggleable__content.fitted {
/* fitted */
background-color: var(--sklearn-color-fitted-level-0);
}
#sk-container-id-4 div.sk-toggleable__content pre {
margin: 0.2em;
border-radius: 0.25em;
color: var(--sklearn-color-text);
/* unfitted */
background-color: var(--sklearn-color-unfitted-level-0);
}
#sk-container-id-4 div.sk-toggleable__content.fitted pre {
/* unfitted */
background-color: var(--sklearn-color-fitted-level-0);
}
#sk-container-id-4 input.sk-toggleable__control:checked~div.sk-toggleable__content {
/* Expand drop-down */
display: block;
width: 100%;
overflow: visible;
}
#sk-container-id-4 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {
content: "▾";
}
/* Pipeline/ColumnTransformer-specific style */
#sk-container-id-4 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {
color: var(--sklearn-color-text);
background-color: var(--sklearn-color-unfitted-level-2);
}
#sk-container-id-4 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {
background-color: var(--sklearn-color-fitted-level-2);
}
/* Estimator-specific style */
/* Colorize estimator box */
#sk-container-id-4 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {
/* unfitted */
background-color: var(--sklearn-color-unfitted-level-2);
}
#sk-container-id-4 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {
/* fitted */
background-color: var(--sklearn-color-fitted-level-2);
}
#sk-container-id-4 div.sk-label label.sk-toggleable__label,
#sk-container-id-4 div.sk-label label {
/* The background is the default theme color */
color: var(--sklearn-color-text-on-default-background);
}
/* On hover, darken the color of the background */
#sk-container-id-4 div.sk-label:hover label.sk-toggleable__label {
color: var(--sklearn-color-text);
background-color: var(--sklearn-color-unfitted-level-2);
}
/* Label box, darken color on hover, fitted */
#sk-container-id-4 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {
color: var(--sklearn-color-text);
background-color: var(--sklearn-color-fitted-level-2);
}
/* Estimator label */
#sk-container-id-4 div.sk-label label {
font-family: monospace;
font-weight: bold;
display: inline-block;
line-height: 1.2em;
}
#sk-container-id-4 div.sk-label-container {
text-align: center;
}
/* Estimator-specific */
#sk-container-id-4 div.sk-estimator {
font-family: monospace;
border: 1px dotted var(--sklearn-color-border-box);
border-radius: 0.25em;
box-sizing: border-box;
margin-bottom: 0.5em;
/* unfitted */
background-color: var(--sklearn-color-unfitted-level-0);
}
#sk-container-id-4 div.sk-estimator.fitted {
/* fitted */
background-color: var(--sklearn-color-fitted-level-0);
}
/* on hover */
#sk-container-id-4 div.sk-estimator:hover {
/* unfitted */
background-color: var(--sklearn-color-unfitted-level-2);
}
#sk-container-id-4 div.sk-estimator.fitted:hover {
/* fitted */
background-color: var(--sklearn-color-fitted-level-2);
}
/* Specification for estimator info (e.g. "i" and "?") */
/* Common style for "i" and "?" */
.sk-estimator-doc-link,
a:link.sk-estimator-doc-link,
a:visited.sk-estimator-doc-link {
float: right;
font-size: smaller;
line-height: 1em;
font-family: monospace;
background-color: var(--sklearn-color-background);
border-radius: 1em;
height: 1em;
width: 1em;
text-decoration: none !important;
margin-left: 0.5em;
text-align: center;
/* unfitted */
border: var(--sklearn-color-unfitted-level-1) 1pt solid;
color: var(--sklearn-color-unfitted-level-1);
}
.sk-estimator-doc-link.fitted,
a:link.sk-estimator-doc-link.fitted,
a:visited.sk-estimator-doc-link.fitted {
/* fitted */
border: var(--sklearn-color-fitted-level-1) 1pt solid;
color: var(--sklearn-color-fitted-level-1);
}
/* On hover */
div.sk-estimator:hover .sk-estimator-doc-link:hover,
.sk-estimator-doc-link:hover,
div.sk-label-container:hover .sk-estimator-doc-link:hover,
.sk-estimator-doc-link:hover {
/* unfitted */
background-color: var(--sklearn-color-unfitted-level-3);
color: var(--sklearn-color-background);
text-decoration: none;
}
div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,
.sk-estimator-doc-link.fitted:hover,
div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,
.sk-estimator-doc-link.fitted:hover {
/* fitted */
background-color: var(--sklearn-color-fitted-level-3);
color: var(--sklearn-color-background);
text-decoration: none;
}
/* Span, style for the box shown on hovering the info icon */
.sk-estimator-doc-link span {
display: none;
z-index: 9999;
position: relative;
font-weight: normal;
right: .2ex;
padding: .5ex;
margin: .5ex;
width: min-content;
min-width: 20ex;
max-width: 50ex;
color: var(--sklearn-color-text);
box-shadow: 2pt 2pt 4pt #999;
/* unfitted */
background: var(--sklearn-color-unfitted-level-0);
border: .5pt solid var(--sklearn-color-unfitted-level-3);
}
.sk-estimator-doc-link.fitted span {
/* fitted */
background: var(--sklearn-color-fitted-level-0);
border: var(--sklearn-color-fitted-level-3);
}
.sk-estimator-doc-link:hover span {
display: block;
}
/* "?"-specific style due to the `<a>` HTML tag */
#sk-container-id-4 a.estimator_doc_link {
float: right;
font-size: 1rem;
line-height: 1em;
font-family: monospace;
background-color: var(--sklearn-color-background);
border-radius: 1rem;
height: 1rem;
width: 1rem;
text-decoration: none;
/* unfitted */
color: var(--sklearn-color-unfitted-level-1);
border: var(--sklearn-color-unfitted-level-1) 1pt solid;
}
#sk-container-id-4 a.estimator_doc_link.fitted {
/* fitted */
border: var(--sklearn-color-fitted-level-1) 1pt solid;
color: var(--sklearn-color-fitted-level-1);
}
/* On hover */
#sk-container-id-4 a.estimator_doc_link:hover {
/* unfitted */
background-color: var(--sklearn-color-unfitted-level-3);
color: var(--sklearn-color-background);
text-decoration: none;
}
#sk-container-id-4 a.estimator_doc_link.fitted:hover {
/* fitted */
background-color: var(--sklearn-color-fitted-level-3);
}
.estimator-table summary {
padding: .5rem;
font-family: monospace;
cursor: pointer;
}
.estimator-table details[open] {
padding-left: 0.1rem;
padding-right: 0.1rem;
padding-bottom: 0.3rem;
}
.estimator-table .parameters-table {
margin-left: auto !important;
margin-right: auto !important;
}
.estimator-table .parameters-table tr:nth-child(odd) {
background-color: #fff;
}
.estimator-table .parameters-table tr:nth-child(even) {
background-color: #f6f6f6;
}
.estimator-table .parameters-table tr:hover {
background-color: #e0e0e0;
}
.estimator-table table td {
border: 1px solid rgba(106, 105, 104, 0.232);
}
.user-set td {
color:rgb(255, 94, 0);
text-align: left;
}
.user-set td.value pre {
color:rgb(255, 94, 0) !important;
background-color: transparent !important;
}
.default td {
color: black;
text-align: left;
}
.user-set td i,
.default td i {
color: black;
}
.copy-paste-icon {
background-image: url(data:image/svg+xml;base64,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);
background-repeat: no-repeat;
background-size: 14px 14px;
background-position: 0;
display: inline-block;
width: 14px;
height: 14px;
cursor: pointer;
}
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
Pipeline(steps=[('dictvectorizer', DictVectorizer()),
('logisticregression', LogisticRegression(solver='liblinear'))])In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
Pipeline
?Documentation for PipelineiFitted
Parameters
| steps | [('dictvectorizer', ...), ('logisticregression', ...)] | |
| transform_input | None | |
| memory | None | |
| verbose | False |
DictVectorizer
Parameters
| dtype | <class 'numpy.float64'> | |
| separator | '=' | |
| sparse | True | |
| sort | True |
LogisticRegression
Parameters
| penalty | 'l2' | |
| dual | False | |
| tol | 0.0001 | |
| C | 1.0 | |
| fit_intercept | True | |
| intercept_scaling | 1 | |
| class_weight | None | |
| random_state | None | |
| solver | 'liblinear' | |
| max_iter | 100 | |
| multi_class | 'deprecated' | |
| verbose | 0 | |
| warm_start | False | |
| n_jobs | None | |
| l1_ratio | None |
In [ ]python · cell 18
python
pipeline.predict_proba(datapoint)[0, 1]Output
np.float64(0.33617994559536546)
In [33]python · cell 19
python
import requestsIn [36]python · cell 20
python
url = 'http://localhost:9696/predict'
customer = {
'gender': 'female',
'seniorcitizen': 0,
'partner': 'yes',
'dependents': 'no',
'phoneservice': 'no',
'multiplelines': 'no_phone_service',
'internetservice': 'dsl',
'onlinesecurity': 'no',
'onlinebackup': 'yes',
'deviceprotection': 'no',
'techsupport': 'no',
'streamingtv': 'no',
'streamingmovies': 'no',
'contract': 'month-to-month',
'paperlessbilling': 'yes',
'paymentmethod': 'electronic_check',
'tenure': 1,
'monthlycharges': 29.85,
'totalcharges': 29.85
}
response = requests.post(url, json=customer)In [38]python · cell 21
python
predictions = response.json()In [39]python · cell 22
python
if predictions['churn']:
print('accept loan application')
else:
print('reject loan application')Output
reject loan application
In [46]python · cell 23
python
for n in numerical:
print(df[n].describe())
print()
for c in categorical:
print(df[c].value_counts())
print()Output
count 7043.000000 mean 32.371149 std 24.559481 min 0.000000 25% 9.000000 50% 29.000000 75% 55.000000 max 72.000000 Name: tenure, dtype: float64 count 7043.000000 mean 64.761692 std 30.090047 min 18.250000 25% 35.500000 50% 70.350000 75% 89.850000 max 118.750000 Name: monthlycharges, dtype: float64 count 7043.000000 mean 2279.734304 std 2266.794470 min 0.000000 25% 398.550000 50% 1394.550000 75% 3786.600000 max 8684.800000 Name: totalcharges, dtype: float64 gender male 3555 female 3488 Name: count, dtype: int64 seniorcitizen 0 5901 1 1142 Name: count, dtype: int64 partner no 3641 yes 3402 Name: count, dtype: int64 dependents no 4933 yes 2110 Name: count, dtype: int64 phoneservice yes 6361 no 682 Name: count, dtype: int64 multiplelines no 3390 yes 2971 no_phone_service 682 Name: count, dtype: int64 internetservice fiber_optic 3096 dsl 2421 no 1526 Name: count, dtype: int64 onlinesecurity no 3498 yes 2019 no_internet_service 1526 Name: count, dtype: int64 onlinebackup no 3088 yes 2429 no_internet_service 1526 Name: count, dtype: int64 deviceprotection no 3095 yes 2422 no_internet_service 1526 Name: count, dtype: int64 techsupport no 3473 yes 2044 no_internet_service 1526 Name: count, dtype: int64 streamingtv no 2810 yes 2707 no_internet_service 1526 Name: count, dtype: int64 streamingmovies no 2785 yes 2732 no_internet_service 1526 Name: count, dtype: int64 contract month-to-month 3875 two_year 1695 one_year 1473 Name: count, dtype: int64 paperlessbilling yes 4171 no 2872 Name: count, dtype: int64 paymentmethod electronic_check 2365 mailed_check 1612 bank_transfer_(automatic) 1544 credit_card_(automatic) 1522 Name: count, dtype: int64
In [ ]python · cell 24
python