Generate advanced model insights¶

%matplotlib inline
import datarobot as dr
from datarobot.enums import AUTOPILOT_MODE
from datarobot.errors import ClientError
import matplotlib.pyplot as plt
import matplotlib.ticker as mtick
import numpy as np
import pandas as pd

# If the config file is not in the default location described in the API Quickstart guide, '~/.config/datarobot/drconfig.yaml', then you will need to call
# dr.Client(config_path='path-to-drconfig.yaml')

model = project.get_top_model()

dr_dark_blue = "#08233F"
dr_blue = "#1F77B4"
dr_orange = "#FF7F0E"
dr_red = "#BE3C28"

feature_impacts = model.get_or_request_feature_impact()

def matplotlib_pair_histogram(labels, counts, target_avgs, bin_count, ax1, feature):
    # Rotate categorical labels
    if feature.feature_type in ["Categorical", "Text"]:
        ax1.tick_params(axis="x", rotation=45)
    ax1.set_ylabel(feature.name, color=dr_blue)
    ax1.bar(labels, counts, color=dr_blue)
    # Instantiate a second axes that shares the same x-axis
    ax2 = ax1.twinx()
    ax2.set_ylabel(target_feature_name, color=dr_orange)
    ax2.plot(labels, target_avgs, marker="o", lw=1, color=dr_orange)
    ax1.set_facecolor(dr_dark_blue)
    title = "Histogram for {} ({} bins)".format(feature.name, bin_count)
    ax1.set_title(title)

def draw_feature_histogram(feature_name, bin_count):
    feature = dr.Feature.get(project.id, feature_name)
    # Retrieve downsampled histogram data from server
    # based on desired bin count
    data = feature.get_histogram(bin_count).plot
    labels = [row["label"] for row in data]
    counts = [row["count"] for row in data]
    target_averages = [row["target"] for row in data]
    f, axarr = plt.subplots()
    f.set_size_inches((10, 4))
    matplotlib_pair_histogram(labels, counts, target_averages, bin_count, axarr, feature)

def rebin_df(raw_df, number_of_bins):
    cols = ["bin", "actual_mean", "predicted_mean", "bin_weight"]
    new_df = pd.DataFrame(columns=cols)
    current_prediction_total = 0
    current_actual_total = 0
    current_row_total = 0
    x_index = 1
    bin_size = 60 / number_of_bins
    for rowId, data in raw_df.iterrows():
        current_prediction_total += data["predicted"] * data["bin_weight"]
        current_actual_total += data["actual"] * data["bin_weight"]
        current_row_total += data["bin_weight"]

        if (rowId + 1) % bin_size == 0:
            x_index += 1
            bin_properties = {
                "bin": ((round(rowId + 1) / 60) * number_of_bins),
                "actual_mean": current_actual_total / current_row_total,
                "predicted_mean": current_prediction_total / current_row_total,
                "bin_weight": current_row_total,
            }

            new_df = new_df.append(bin_properties, ignore_index=True)
            current_prediction_total = 0
            current_actual_total = 0
            current_row_total = 0
    return new_df


def matplotlib_lift(bins_df, bin_count, ax):
    grouped = rebin_df(bins_df, bin_count)
    ax.plot(range(1, len(grouped) + 1), grouped["predicted_mean"], marker="+", lw=1, color=dr_blue)
    ax.plot(range(1, len(grouped) + 1), grouped["actual_mean"], marker="*", lw=1, color=dr_orange)
    ax.set_xlim([0, len(grouped) + 1])
    ax.set_facecolor(dr_dark_blue)
    ax.legend(loc="best")
    ax.set_title("Lift chart {} bins".format(bin_count))
    ax.set_xlabel("Sorted Prediction")
    ax.set_ylabel("Value")
    return grouped