# Clone repository
git clone -b prod git@mygithub.gsk.com:to561778/hci-tools.git

# Install package
python -m pip install -e hci-tools

# Clone the repository
git clone -b dev git@mygithub.gsk.com:to561778/hci-tools.git
cd hci-tools

# Create conda environment
conda env create -f environment.yml
conda activate hcitools

# Install the package
python -m pip install -e .

# Import
from hcitools import datasets, plot

# Load datasets
covid = datasets.load_dataset('covid')
ros = datasets.load_dataset('ros-mito')

# Plotly renderer
plot.set_renderer('notebook')  # Use this when running notebook
plot.set_renderer('iframe_connected')  # Use this when rendering docs

# Prepare data frame
data = (covid.copy()
    .filter(regex='^B-', axis=1))  # Keep only blood markers
metadata =  covid[['Mortality', 'Sex']]
data.columns = [x[2:] for x in data.columns]

# Define groups for heatmap
row_groups = {
    k: list(v.values()) for k, v in metadata.to_dict(orient='index').items()
}
row_group_names = ['Mortality', 'Sex']
row_colors = {'Alive': '#38d652', 'Dead': '#d93e38',
              'Male': 'blue', 'Female': 'pink'}

# Create heatmap
fig = plot.heatmap(
    data=data,
    clust_rows=True,
    clust_cols=True,
    row_colors=row_colors,
    row_groups=row_groups,
    row_group_names=row_group_names
)

# Add a title and tweak the size
fig.update_layout(
    title='Blood Biomarkers',
    title_x=0.5,
    height=400,
    width=700
)

# Annotate highly expressed proteins
fig.add_shape(
    type='rect',
    x0='MCP-1', x1='EGF',
    y0=0, y1=88,
    row=1, col=3,
    line=dict(color='black')
)

fig.show()

# Prepare data frame
vars = ['APACHE1h', 'APACHE24h', 'CCI']
data = (covid.copy()
    .set_index(vars)
    .filter(regex='^B-')
    .reset_index()
    .corr()
    .loc[vars, :]
    .drop(vars, axis=1))
data.columns = [x[2:] for x in data.columns]

# Create heatmap
fig = plot.heatmap(
    data=data,
    clust_cols=True,
    clust_rows=True
)

fig.update_layout(
    title='Correlation with Clinical Severity',
    title_x=0.5,
    height=400,
    width=700
)

# Show ticks on the y axis (these are hidden by default)
fig.update_yaxes(
    showticklabels=True, 
    tickfont_size=14
)


fig.show()

fig = plot.plate_heatmap(
    data=ros,
    feature="Non-border cells - Number of Objects"
)
fig.update_layout(width=900, height=500)

fig.show()

# Imports
from hcitools import datasets, plot, analysis, preprocess

# Load dataset
ros = datasets.load_dataset('ros-mito')

# Plotly renderer
plot.set_renderer('notebook')  # Use this when running notebook
plot.set_renderer('iframe_connected')  # Use this when rendering docs

# Preprocessing
meta = ['Well', 'Row', 'Column', 'Timepoint', 'Compound', 'Conc']
df, dropped, LOG = preprocess.clean_data(
    data=ros,
    metacols=meta,
    dropna=True,
    drop_low_var=0.0,
    corr_thresh=0.9,
    verbose=True
)
df = df.set_index(meta)

# Generate clusters with default arguments
proj, expvar = analysis.dim_reduction(data=df, method=['pca', 'tsne'])

# Plot PCA components
fig = plot.pca_comps(proj, expvar, n_comps=3)
fig.update_layout(width=700, height=400)

fig.show()

# Compare 2 compounds
fig = plot.clusters(proj, 'Sorafenib Tosylate', 'Imatinib mesylate', 'tsne')
fig.update_layout(width=750, height=450)

fig.show()