Skip to content

Stratifier

Warning

This library is under development, none of the presented solutions are available for download.

With this module, you will be able to obtain assistance in the stratification process of your plantations. Use forest inventory data to automatically stratify the plantations, selecting the forest variables you consider most relevant and either using a predefined number of strata or allowing the module to determine the optimal number of strata.

Class Parameters

Stratifier

Stratifier(df, y, *train_columns, iterator=None)
Parameters Description
df The dataframe containing the forest inventory data.
*groups_columns Columns that will be used for stratification. Numeric only.
iterator (Optional) The stratification will be performed for each iterator.

Class Functions

functions and parameters
Stratifier.stratify_kmeans(k=None, k_method=None, max_k=100,
                          show_plots=True, save_plots_dir=None)#(1)!

Stratifier.stratify_hierarchical(k=None, k_method=None, max_k=10,
                                show_plots=True, save_plots_dir=None)#(2)!

  1. k = (Optional) Desired number of strata.
    k_method = (Optional) If k is not specified, which method will be used to define the number of k. Options: elbow, silhouette, davies_bouldin, calinski_harabasz. Default = "elbow".
    max_k = (Optional) Maximum number of strata to be created.
    show_plots = If true, displays the radar chart with the generated strata.
    save_plot_dir = (Optional) Directory to save the plots of the generated strata.
  2. k = (Optional) Desired number of strata.
    k_method = (Optional) If k is not specified, which method will be used to define the number of k. Options: elbow, silhouette, davies_bouldin, calinski_harabasz. Default = "elbow".
    max_k = (Optional) Maximum number of strata to be created.
    show_plots = If true, displays the radar chart with the generated strata.
    save_plot_dir = (Optional) Directory to save the plots of the generated strata.
Parameters Description
.stratify_kmeans() Performs stratification using the K-Means algorithm.
.stratify_hierarchical() Performs stratification using the Agglomerative Clustering algorithm.

Example Usage

stratifier_example.py
1
2
from fptools.stratifier import Stratifier#(1)!
import pandas as pd#(2)!

  1. Import Stratifier class.
  2. Import pandas for data manipulation.

stratifier_example.py
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
df = pd.read_csv(r'C:\Your\path\inventory_data.csv')#(1)!

columns_used_for_stratification = [
                            "age",
                            "shafts",
                            "basal-area",
                            "HMAX",
                            "DMAX",
                            "DG"
                            ]#(2)!

st = Stratifier(df, *columns_used_for_training, iterator="City")#(3)!

stratified_df = st.stratify_kmeans()#(4)!

  1. Load your CSV file containing the inventory data.
  2. Create a lista called columns_used_for_stratification containing the columns that will be used for the stratification.
  3. Creates the variable st using the dataframe df, passing the columns columns_used_for_training as stratification parameters and using the column City as an iterator.
  4. Performs stratification using the "KMeans" algorithm, allowing the algorithm to determine the number of strata. Save the results in stratified_df variable.