使用 Gradio 实现表格数据科学工作流

import gradio as gr
import pandas as pd
import joblib
import datasets


inputs = [gr.Dataframe(row_count = (2, "dynamic"), col_count=(4,"dynamic"), label="Input Data", interactive=1)]

outputs = [gr.Dataframe(row_count = (2, "dynamic"), col_count=(1, "fixed"), label="Predictions", headers=["Failures"])]

model = joblib.load("model.pkl")

# we will give our dataframe as example
df = datasets.load_dataset("merve/supersoaker-failures")
df = df["train"].to_pandas()

def infer(input_dataframe):
  return pd.DataFrame(model.predict(input_dataframe))

gr.Interface(fn = infer, inputs = inputs, outputs = outputs, examples = [[df.head(2)]]).launch()

import gradio as gr
import pandas as pd
import datasets
import seaborn as sns
import matplotlib.pyplot as plt

df = datasets.load_dataset("merve/supersoaker-failures")
df = df["train"].to_pandas()
df.dropna(axis=0, inplace=True)

def plot(df):
  plt.scatter(df.measurement_13, df.measurement_15, c = df.loading,alpha=0.5)
  plt.savefig("scatter.png")
  df['failure'].value_counts().plot(kind='bar')
  plt.savefig("bar.png")
  sns.heatmap(df.select_dtypes(include="number").corr())
  plt.savefig("corr.png")
  plots = ["corr.png","scatter.png", "bar.png"]
  return plots

inputs = [gr.Dataframe(label="Supersoaker Production Data")]
outputs = [gr.Gallery(label="Profiling Dashboard", columns=(1,3))]

gr.Interface(plot, inputs=inputs, outputs=outputs, examples=[df.head(100)], title="Supersoaker Failures Analysis Dashboard").launch()

import gradio as gr

# title and description are optional
title = "Supersoaker Defective Product Prediction"
description = "This model predicts Supersoaker production line failures. Drag and drop any slice from dataset or edit values as you wish in below dataframe component."

gr.load("huggingface/scikit-learn/tabular-playground", title=title, description=description).launch()