Skip to content
Competition - predicting concrete strength - Concrete Mathic
  • AI Chat
  • Code
  • Report
    • Spinner

    Concrete Mathic 🤖🪄

    Hidden code

    💾 The data

    Compressive strength data:
    • "cement" - Portland cement in kg/m3
    • "slag" - Blast furnace slag in kg/m3
    • "fly_ash" - Fly ash in kg/m3
    • "water" - Water in liters/m3
    • "superplasticizer" - Superplasticizer additive in kg/m3
    • "coarse_aggregate" - Coarse aggregate (gravel) in kg/m3
    • "fine_aggregate" - Fine aggregate (sand) in kg/m3
    • "age" - Age of the sample in days
    • "strength" - Concrete compressive strength in megapascals (MPa)

    Acknowledgments: I-Cheng Yeh, "Modeling of strength of high-performance concrete using artificial neural networks," Cement and Concrete Research, Vol. 28, No. 12, pp. 1797-1808 (1998).

    Hidden code

    The average strength 🦾

    df_avg_str_sel = df[['strength', 'age']]
df_avg_str = df_avg_str_sel.groupby('age').mean().reset_index()
df_avg_s = df_avg_str[df_avg_str['age'] == 1].append(df_avg_str[df_avg_str['age'] == 7]).append(df_avg_str[df_avg_str['age'] == 14]).append(df_avg_str[df_avg_str['age'] == 28])
display(df_avg_s.rename({'strength' : 'avg. strength'}, axis=1).set_index('age').T)

    🧮 Coefficients

    Let's take a short look on the dataset correlation:

    df_corr = df.corr()
mask = np.zeros_like(df_corr)
mask[np.triu_indices_from(mask)] = True
with sns.axes_style("white"):
    f, heatmap = plt.subplots(figsize=(12, 6))
    heatmap = sns.heatmap(df_corr, cmap="vlag", mask=mask, linewidths=1, annot=True).set(title='Correlation matrix')
plt.xticks(rotation=60)
plt.show()

    We need to find the coefficients for the formula:

    🤖🪄 Developing a machine learning model for find the coefficients:

    Hidden code
    Hidden code

    Checking 🔎

    Both the models gieves nearble equal coefficients, but because the Gradient Boosting predictive acciracy is higher, we'll use its coefficients for

    ‌
    ‌
    ‌