Spaces:
Sleeping
Sleeping
File size: 9,039 Bytes
323ef01 1733b93 323ef01 1733b93 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 |
import streamlit as st
import seaborn as sns
import matplotlib.pyplot as plt
import matplotlib.dates as mdates
import pandas as pd
# Load data
def load_data():
df = pd.read_csv("./processed_data.csv") # Replace with your dataset
return df
# Create Streamlit app
def app():
# Title for the app
huggingface_page_title = "Machine Tool Failure Dashboard"
st.set_page_config(page_title=huggingface_page_title, layout="wide")
# --- Custom CSS to adjust sidebar width ---
st.markdown(
"""
<style>
/* Sidebar width */
[data-testid="stSidebar"] {
width: 600px;
min-width: 600px;
}
</style>
""",
unsafe_allow_html=True
)
# --- Page content ---
st.title(huggingface_page_title)
# Load data
data = load_data()
# --- Create some helper/derived columns ---
# Kelvin -> Celsius for readability (if temps exist)
if "Air temperature" in data.columns:
data["Air temperature (°C)"] = data["Air temperature"] - 273.15
if "Process temperature" in data.columns:
data["Process temperature (°C)"] = data["Process temperature"] - 273.15
# Temperature delta (process - air)
if {"Air temperature", "Process temperature"}.issubset(data.columns):
data["Temperature delta (°C)"] = data["Process temperature"] - data["Air temperature"]
# Rotational speed categories (quartiles)
if "Rotational speed" in data.columns:
try:
data["Rotational speed category"] = pd.qcut(
data["Rotational speed"],
q=4,
labels=["Very Low", "Low", "High", "Very High"]
)
except ValueError:
# qcut can fail if there are too many identical values; fallback to cut
data["Rotational speed category"] = pd.cut(
data["Rotational speed"],
bins=4,
labels=["Very Low", "Low", "High", "Very High"]
)
# --- Key Metrics from the data ---
total_obs = len(data)
n_failures = int(data["Failure"].sum()) if "Failure" in data.columns else 0
failure_rate = (n_failures / total_obs * 100) if total_obs > 0 else 0
n_types = data["Type"].nunique() if "Type" in data.columns else 0
most_common_type = data["Type"].value_counts().idxmax() if "Type" in data.columns else "N/A"
avg_rot_speed = round(data["Rotational speed"].mean(), 2) if "Rotational speed" in data.columns else None
avg_torque = round(data["Torque"].mean(), 2) if "Torque" in data.columns else None
avg_tool_wear = round(data["Tool wear"].mean(), 2) if "Tool wear" in data.columns else None
avg_air_temp_c = (
round(data["Air temperature (°C)"].mean(), 2)
if "Air temperature (°C)" in data.columns
else None
)
avg_proc_temp_c = (
round(data["Process temperature (°C)"].mean(), 2)
if "Process temperature (°C)" in data.columns
else None
)
avg_temp_delta = (
round(data["Temperature delta (°C)"].mean(), 2)
if "Temperature delta (°C)" in data.columns
else None
)
# Display metrics in the sidebar
st.sidebar.header("Key Metrics")
st.sidebar.metric("Total observations", total_obs)
st.sidebar.metric("Number of failures", n_failures)
st.sidebar.metric("Failure rate (%)", f"{failure_rate:.2f}")
st.sidebar.metric("Number of machine types", n_types)
st.sidebar.metric("Most common type", most_common_type)
if avg_rot_speed is not None:
st.sidebar.metric("Avg rotational speed (RPM)", avg_rot_speed)
if avg_torque is not None:
st.sidebar.metric("Avg torque (Nm)", avg_torque)
if avg_tool_wear is not None:
st.sidebar.metric("Avg tool wear (min)", avg_tool_wear)
if avg_air_temp_c is not None:
st.sidebar.metric("Avg air temperature (°C)", avg_air_temp_c)
if avg_proc_temp_c is not None:
st.sidebar.metric("Avg process temperature (°C)", avg_proc_temp_c)
if avg_temp_delta is not None:
st.sidebar.metric("Avg temp delta (°C)", avg_temp_delta)
st.markdown("### Data preview")
st.dataframe(data.head())
sns.set_style("whitegrid", {'grid.color': 'lightgrey', 'grid.linestyle': '--'})
#////////////////////////////////////////////////////////////////////////////
# Failure distribution
#////////////////////////////////////////////////////////////////////////////
if "Failure" in data.columns:
st.header("Failure distribution")
fig, ax = plt.subplots()
failure_counts = data["Failure"].value_counts().sort_index()
sns.barplot(x=failure_counts.index, y=failure_counts.values, ax=ax)
ax.set_xlabel("Failure (0 = No, 1 = Yes)")
ax.set_ylabel("Count")
ax.set_title("Failure Count")
for i, v in enumerate(failure_counts.values):
ax.text(i, v + max(failure_counts.values) * 0.01, str(v), ha="center", va="bottom", fontsize=9)
st.pyplot(fig)
plt.show()
#////////////////////////////////////////////////////////////////////////////
# Failure rate by machine Type
#////////////////////////////////////////////////////////////////////////////
if {"Type", "Failure"}.issubset(data.columns):
st.header("Failure rate by machine type")
fig, ax = plt.subplots()
failure_by_type = data.groupby("Type")["Failure"].mean().reset_index()
failure_by_type["Failure_rate_%"] = failure_by_type["Failure"] * 100
sns.barplot(data=failure_by_type, x="Type", y="Failure_rate_%", ax=ax)
ax.set_ylabel("Failure rate (%)")
ax.set_title("Failure rate by machine type")
for i, row in failure_by_type.iterrows():
ax.text(i, row["Failure_rate_%"] + 0.5, f"{row['Failure_rate_%']:.1f}%", ha="center", fontsize=9)
st.pyplot(fig)
plt.show()
#////////////////////////////////////////////////////////////////////////////
# Rotational speed distribution by failure
#////////////////////////////////////////////////////////////////////////////
if {"Rotational speed", "Failure"}.issubset(data.columns):
st.header("Rotational speed distribution by failure")
fig, ax = plt.subplots()
sns.histplot(
data=data,
x="Rotational speed",
hue="Failure",
multiple="stack",
bins=30,
ax=ax
)
ax.set_xlabel("Rotational speed (RPM)")
ax.set_title("Rotational speed distribution (Failed vs Not Failed)")
st.pyplot(fig)
plt.show()
#////////////////////////////////////////////////////////////////////////////
# Torque vs Rotational speed (scatter)
#////////////////////////////////////////////////////////////////////////////
if {"Torque", "Rotational speed"}.issubset(data.columns):
st.header("Torque vs Rotational speed")
fig, ax = plt.subplots()
if "Failure" in data.columns:
sns.scatterplot(
data=data,
x="Rotational speed",
y="Torque",
hue="Failure",
alpha=0.6,
ax=ax
)
else:
sns.scatterplot(
data=data,
x="Rotational speed",
y="Torque",
alpha=0.6,
ax=ax
)
ax.set_xlabel("Rotational speed (RPM)")
ax.set_ylabel("Torque (Nm)")
ax.set_title("Torque vs Rotational speed")
st.pyplot(fig)
plt.show()
#////////////////////////////////////////////////////////////////////////////
# Tool wear distribution by failure
#////////////////////////////////////////////////////////////////////////////
if {"Tool wear", "Failure"}.issubset(data.columns):
st.header("Tool wear distribution by failure")
fig, ax = plt.subplots()
sns.boxplot(
data=data,
x="Failure",
y="Tool wear",
ax=ax
)
ax.set_xlabel("Failure (0 = No, 1 = Yes)")
ax.set_ylabel("Tool wear (min)")
ax.set_title("Tool wear vs Failure")
st.pyplot(fig)
plt.show()
#////////////////////////////////////////////////////////////////////////////
# Correlation heatmap of numeric variables
#////////////////////////////////////////////////////////////////////////////
st.header("Correlation heatmap (numeric features)")
numeric_cols = data.select_dtypes(include=["number"]).columns
if len(numeric_cols) > 1:
fig, ax = plt.subplots(figsize=(8, 6))
corr = data[numeric_cols].corr()
sns.heatmap(corr, annot=True, fmt=".2f", cmap="coolwarm", ax=ax)
ax.set_title("Correlation heatmap")
st.pyplot(fig)
plt.show()
else:
st.write("Not enough numeric columns to compute correlations.")
if __name__ == "__main__":
app()
|