Spaces:
Runtime error
Runtime error
Mariusz Kossakowski
commited on
Commit
•
47923e1
1
Parent(s):
39df437
Add searching for a specific word
Browse files
app.py
CHANGED
@@ -83,6 +83,7 @@ DATA_DICT, DATA_DESCRIPTION = load_hf_dataset()
|
|
83 |
header = st.container()
|
84 |
description = st.container()
|
85 |
dataframe_head = st.container()
|
|
|
86 |
dataset_statistics = st.container()
|
87 |
|
88 |
with header:
|
@@ -96,11 +97,17 @@ with dataframe_head:
|
|
96 |
filtering_options = DATA_DICT["train"]["target"].unique().tolist()
|
97 |
filtering_options.append("All classes")
|
98 |
|
99 |
-
st.header("First 10 observations of
|
100 |
class_to_show = st.selectbox(
|
101 |
label="Select class to show", options=filtering_options
|
102 |
)
|
103 |
-
df_to_show =
|
|
|
|
|
|
|
|
|
|
|
|
|
104 |
if class_to_show == "All classes":
|
105 |
df_to_show = df_to_show.head(10)
|
106 |
else:
|
@@ -108,6 +115,20 @@ with dataframe_head:
|
|
108 |
st.dataframe(df_to_show)
|
109 |
st.text_area(label="Latex code", value=df_to_show.style.to_latex())
|
110 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
111 |
with dataset_statistics:
|
112 |
st.header("Dataset statistics")
|
113 |
st.subheader("Number of samples in each data split")
|
|
|
83 |
header = st.container()
|
84 |
description = st.container()
|
85 |
dataframe_head = st.container()
|
86 |
+
word_searching = st.container()
|
87 |
dataset_statistics = st.container()
|
88 |
|
89 |
with header:
|
|
|
97 |
filtering_options = DATA_DICT["train"]["target"].unique().tolist()
|
98 |
filtering_options.append("All classes")
|
99 |
|
100 |
+
st.header("First 10 observations of a chosen class")
|
101 |
class_to_show = st.selectbox(
|
102 |
label="Select class to show", options=filtering_options
|
103 |
)
|
104 |
+
df_to_show = pd.concat(
|
105 |
+
[
|
106 |
+
DATA_DICT["train"].copy(),
|
107 |
+
DATA_DICT["validation"].copy(),
|
108 |
+
DATA_DICT["test"].copy(),
|
109 |
+
]
|
110 |
+
)
|
111 |
if class_to_show == "All classes":
|
112 |
df_to_show = df_to_show.head(10)
|
113 |
else:
|
|
|
115 |
st.dataframe(df_to_show)
|
116 |
st.text_area(label="Latex code", value=df_to_show.style.to_latex())
|
117 |
|
118 |
+
with word_searching:
|
119 |
+
st.header("Observations containing a chosen word")
|
120 |
+
searched_word = st.text_input(label="Enter the word you are looking for below")
|
121 |
+
df_to_show = pd.concat(
|
122 |
+
[
|
123 |
+
DATA_DICT["train"].copy(),
|
124 |
+
DATA_DICT["validation"].copy(),
|
125 |
+
DATA_DICT["test"].copy(),
|
126 |
+
]
|
127 |
+
)
|
128 |
+
df_to_show = df_to_show.loc[df_to_show["text"].str.contains(searched_word)]
|
129 |
+
st.dataframe(df_to_show)
|
130 |
+
st.text_area(label="Latex code", value=df_to_show.style.to_latex())
|
131 |
+
|
132 |
with dataset_statistics:
|
133 |
st.header("Dataset statistics")
|
134 |
st.subheader("Number of samples in each data split")
|