| x = [1,2,3] | |
| def test(): | |
| print("x-slice id before",id(x[:])) | |
| print("x-slice before", x[:]) | |
| x[:] += [4] | |
| print("x-slice id after",id(x[:])) | |
| print("x-slice after", x[:]) | |
| print("x id", id(x)) |
| #!/usr/bin/python | |
| def merge(l): | |
| # Base case | |
| if len(l) < 2: | |
| return l | |
| mid = len(l) // 2 | |
| y = merge(l[:mid]) |
| from IPython.display import HTML | |
| HTML('''<script> | |
| code_show=true; | |
| function code_toggle() { | |
| if (code_show){ | |
| $('div.input').hide(); | |
| } else { | |
| $('div.input').show(); | |
| } |
| ## Split into holdout for purposes of imputation and encoding | |
| X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = .2, random_state=2019) | |
| class_labels = df['segment_label'].cat.categories | |
| ## Preprocessing pipeline | |
| # Define transforms on numeric types | |
| numeric_features = X.select_dtypes(np.number).columns | |
| numeric_transformer = Pipeline(steps=[ | |
| ('imputer', SimpleImputer(strategy='median')), |
| import numpy as np | |
| import matplotlib.pyplot as plt | |
| def plot_stacked_bar(data, series_labels, category_labels=None, | |
| show_values=False, value_format="{}", y_label=None, | |
| colors=None, grid=True, reverse=False): | |
| """Plots a stacked bar chart with the data and labels provided. | |
| Keyword arguments: | |
| data -- 2-dimensional numpy array or nested list |
| def dataframe_difference(df1, df2, which=None): | |
| """Find rows which are different.""" | |
| comparison_df = df1.merge(df2, | |
| indicator=True, | |
| how='outer') | |
| if which is None: | |
| diff_df = comparison_df[comparison_df['_merge'] != 'both'] | |
| else: | |
| diff_df = comparison_df[comparison_df['_merge'] == which] | |
| diff_df.to_csv('data/diff.csv') |
| import datetime | |
| # Filename function for logging | |
| def dt_filename( | |
| filename: str, | |
| extension: str, | |
| path: str = "", | |
| date: str = str(datetime.datetime.now()), | |
| ) -> str: | |
| filename = "_".join([filename, date]) |
| def substring_list_match(string_list, substr_list): | |
| return [target_str for target_str in string_list if any(search_str in target_str for search_str in substr_list)] |
| from IPython.core.display import display, HTML | |
| def display_side_by_side(dfs:list, captions:list): | |
| """Display tables side by side to save vertical space | |
| Input: | |
| dfs: list of pandas.DataFrame | |
| captions: list of table captions | |
| """ | |
| output = "" | |
| combined = dict(zip(captions, dfs)) |
If a project has to have multiple git repos (e.g. Bitbucket and Github) then it's better that they remain in sync.
Usually this would involve pushing each branch to each repo in turn, but actually Git allows pushing to multiple repos in one go.
If in doubt about what git is doing when you run these commands, just
