random_forest_regressor_amangel.py

# -*- coding: utf-8 -*-
"""random_forest_regressor_amangel.ipynb

Automatically generated by Colaboratory.

Original file is located at
    https://colab.research.google.com/drive/1WcyIbIh_vqP32rKWinXKxCmgGhCFzRsk

## import libraries and dataset
"""

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt

dataset = pd.read_csv("yiyao_df3.csv")

print(dataset)

dataset.head()

"""# rearrange column"""

df_reorder = dataset[['Gender','Ethnicity', 'DevType',  'Hobbyist', 'Employment', 'Country', 'EdLevel', 'UndergradMajor', 'OrgSize', 'Year', 'Age',  'LanguageWorkedWith', 'DatabaseWorkedWith', 'YearsCodePro', 'ConvertedComp']] # rearrange column here
df_reorder.to_csv('reorder.csv', index=False)

dataset1 = pd.read_csv("reorder.csv")

dataset1.head()

"""## remove excess numbers after decimal """

dataset2 = pd.read_csv("reorder.csv")
dataset2 = dataset2.round()
dataset2.head()

"""# split dataset"""

x = dataset1.iloc[:, -5:-1].values
y = dataset1.iloc[:, -1].values

print(x)

print(y)

"""## removing 'NaN' from datset"""

x = np.nan_to_num(x)
y = np.nan_to_num(y)

"""## Splitting the dataset into the Training set and Test set"""

from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(x, y, test_size = 0.2, random_state = 0)

"""## Training the Random forest regressor model"""

from sklearn.ensemble import RandomForestRegressor
regressor = RandomForestRegressor(n_estimators = 10, random_state = 0)
regressor.fit(X_train, y_train)

"""## Predicting the Test set results"""

y_pred = regressor.predict(X_test)
np.set_printoptions(precision=2)
print(np.concatenate((y_pred.reshape(len(y_pred),1), y_test.reshape(len(y_test),1)),1))

"""## Evaluating the Model Performance"""

from sklearn.metrics import r2_score
r2_score(y_test, y_pred)