Competition - Bee friendly plants

Which plants are better for bees: native or non-native?

📖 Background

You work for the local government environment agency and have taken on a project about creating pollinator bee-friendly spaces. You can use both native and non-native plants to create these spaces and therefore need to ensure that you use the correct plants to optimize the environment for these bees.

The team has collected data on native and non-native plants and their effects on pollinator bees. Your task will be to analyze this data and provide recommendations on which plants create an optimized environment for pollinator bees.

💾 The Data

You have assembled information on the plants and bees research in a file called plants_and_bees.csv. Each row represents a sample that was taken from a patch of land where the plant species were being studied.

Column	Description
`sample_id`	The ID number of the sample taken.
`species_num`	The number of different bee species in the sample.
`date`	Date the sample was taken.
`season`	Season during sample collection ("early.season" or "late.season").
`site`	Name of collection site.
`native_or_non`	Whether the sample was from a native or non-native plant.
`sampling`	The sampling method.
`plant_species`	The name of the plant species the sample was taken from. None indicates the sample was taken from the air.
`time`	The time the sample was taken.
`bee_species`	The bee species in the sample.
`sex`	The gender of the bee species.
`specialized_on`	The plant genus the bee species preferred.
`parasitic`	Whether or not the bee is parasitic (0:no, 1:yes).
`nesting`	The bees nesting method.
`status`	The status of the bee species.
`nonnative_bee`	Whether the bee species is native or not (0:no, 1:yes).

Source (data has been modified)

💪 Challenge

Provide your agency with a report that covers the following:

Which plants are preferred by native vs non-native bee species?
A visualization of the distribution of bee and plant species across one of the samples.
Select the top three plant species you would recommend to the agency to support native bees.

🧑‍⚖️ Judging criteria

This is a community-based competition. The top 5 most upvoted entries will win.

The winners will receive DataCamp merchandise.

✅ Checklist before publishing

Rename your workspace to make it descriptive of your work. N.B. you should leave the notebook name as notebook.ipynb.
Remove redundant cells like the judging criteria, so the workbook is focused on your work.
Check that all the cells run without error.

⌛️ Time is ticking. Good luck!

import pandas as pd
data = pd.read_csv("data/plants_and_bees.csv")
data

Importing modules

import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn.impute import SimpleImputer
from sklearn.impute import KNNImputer

from sklearn.model_selection import cross_val_score
from sklearn.model_selection import train_test_split
from sklearn.metrics import classification_report

from sklearn.dummy import DummyClassifier
from sklearn.ensemble import RandomForestClassifier
from sklearn.linear_model import LogisticRegression
from sklearn.svm import SVC
import xgboost as bst

Looking into the data types

This will allow me to see if the data is in the correct format.

data.info()

Changing the Dtypes

I find this is useful before looking at any of the decriptive information do to the way numeric and alpha-type data are portrayed. This will also allow me to interrogate missing values.

sampleid will become the indes
species num is fine as an int
date to become date time
season only has 2 so will be one hot encoded
site has 3 options, A, B, C so can be encoded
native_or_non is binary
sampling is binary again
plant_species has 24 options - Target
time list of ints that can be retained#
bee_species 93 different species - try one hot encoding
sex binary
specialized_on - mostly nan, likely drop
parasitic - binary
nesting - 6 types for encoding
status - only 15, likely drop
nonnative_bee = binary imbalanced

# instantiating imputers for missing values
s_imp_para = SimpleImputer() # parasite
k_imp_para = KNNImputer() # parasite
s_imp_nest = SimpleImputer() # nesting
k_imp_nest = KNNImputer() # nesting
s_imp_nnat = SimpleImputer() # nonnative
k_imp_nnat = KNNImputer() # nonnative

# simple imputations
data['parasitic'] = s_imp_para.fit_transform(data['parasitic'].values.reshape(-1,1))
data['nesting'] = data['nesting'].fillna('ground')
data['nonnative_bee'] = s_imp_nnat.fit_transform(data['nonnative_bee'].values.reshape(-1,1))

# converting column types
data_drop = data.drop(columns=['status', 'specialized_on'], axis=1).copy()
data_drop['date'] = pd.to_datetime(data_drop['date']) # date to date_time
data_drop['year'] = data_drop['date'].dt.year
data_drop['month'] = data_drop['date'].dt.month
data_drop['day'] = data_drop['date'].dt.day
data_drop['hour'] = data_drop['date'].dt.hour
data_drop['day_of_week'] = data_drop['date'].dt.dayofweek
data_drop['is_weekend'] = data_drop['date'].dt.weekday >= 5
data_drop = data_drop.drop(columns=['date'], axis=1)
data_drop['plant_species'] = data_drop['plant_species'].str.replace('None', 'air')
data_drop['plant_species'] = pd.factorize(data_drop['plant_species'])[0]

columns_to_encode = ['native_or_non', 'season', 'site', 'sampling', 'bee_species', 'sex', 'parasitic', 'nesting', 'nonnative_bee']

data_encoded = pd.get_dummies(data_drop, columns=columns_to_encode, drop_first=True)
df_shape = data_encoded.shape

data_encoded.set_index('sample_id')
# df_shape = data_drop.shape

print(f"There are {df_shape[0]} rows and {df_shape[1]} columns")

‌
‌
‌